Compare commits

..

89 Commits

Author SHA1 Message Date
Konstantin Osipov
fd293768e7 storage_proxy: do not touch all_replicas.front() if it's empty.
The list of all endpoints for a query can be empty if we have
replication_factor 0 or there are no live endpoints for this token.
Do not access all_replicas.front() in this case.

Fixes #5935.
Message-Id: <20200306192521.73486-2-kostja@scylladb.com>

(cherry picked from commit 9827efe554)
2020-06-22 18:29:15 +03:00
Gleb Natapov
22dfa48585 cql transport: do not log broken pipe error when a client closes its side of a connection abruptly
Fixes #5661

Message-Id: <20200615075958.GL335449@scylladb.com>
(cherry picked from commit 7ca937778d)
2020-06-21 13:09:22 +03:00
Benny Halevy
2f3d7f1408 cql3::util::maybe_quote: avoid stack overflow and fix quote doubling
The function was reimplemented to solve the following issues.
The cutom implementation also improved its performance in
close to 19%

Using regex_match("[a-z][a-z0-9_]*") may cause stack overflow on long input strings
as found with the limits_test.py:TestLimits.max_key_length_test dtest.

std::regex_replace does not replace in-place so no doubling of
quotes was actually done.

Add unit test that reproduces the crash without this fix
and tests various string patterns for correctness.

Note that defining the regex with std::regex::optimize
still ended up with stack overflow.

Fixes #5671

Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
(cherry picked from commit 0329fe1fd1)
2020-06-21 13:07:21 +03:00
Gleb Natapov
76a08df939 commitlog: fix size of a write used to zero a segment
Due to a bug the entire segment is written in one huge write of 32Mb.
The idea was to split it to writes of 128K, so fix it.

Fixes #5857

Message-Id: <20200220102939.30769-1-gleb@scylladb.com>
(cherry picked from commit df2f67626b)
2020-06-21 13:03:05 +03:00
Amnon Heiman
6aa129d3b0 api/storage_service.cc: stream result of token_range
The get token range API can become big which can cause large allocation
and stalls.

This patch replace the implementation so it would stream the results
using the http stream capabilities instead of serialization and sending
one big buffer.

Fixes #6297

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
(cherry picked from commit 7c4562d532)
2020-06-21 12:57:48 +03:00
Takuya ASADA
b4f781e4eb scylla_post_install.sh: fix operator precedence issue with multiple statements
In bash, 'A || B && C' will be problem because when A is true, then it will be
evaluates C, since && and || have the same precedence.
To avoid the issue we need make B && C in one statement.

Fixes #5764

(cherry picked from commit b6988112b4)
2020-06-21 12:47:05 +03:00
Takuya ASADA
27594ca50e scylla_raid_setup: create missing directories
We need to create hints, view_hints, saved_caches directories
on RAID volume.

Fixes #5811

(cherry picked from commit 086f0ffd5a)
2020-06-21 12:45:27 +03:00
Rafael Ávila de Espíndola
0f2f0d65d7 configure: Reduce the dynamic linker path size
gdb has a SO_NAME_MAX_PATH_SIZE of 512, so we use that as the path
size.

Fixes: #6494

Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
Message-Id: <20200528202741.398695-2-espindola@scylladb.com>
(cherry picked from commit aa778ec152)
2020-06-21 12:29:16 +03:00
Tomasz Grabiec
31c2f8a3ae row_cache: Fix undefined behavior on key linearization
This is relevant only when using partition or clustering keys which
have a representation in memory which is larger than 12.8 KB (10% of
LSA segment size).

There are several places in code (cache, background garbage
collection) which may need to linearize keys because of performing key
comparison, but it's not done safely:

 1) the code does not run with the LSA region locked, so pointers may
get invalidated on linearization if it needs to reclaim memory. This
is fixed by running the code inside an allocating section.

 2) LSA region is locked, but the scope of
with_linearized_managed_bytes() encloses the allocating section. If
allocating section needs to reclaim, linearization context will
contain invalidated pointers. The fix is to reorder the scopes so
that linearization context lives within an allocating section.

Example of 1 can be found in
range_populating_reader::handle_end_of_stream() where it performs a
lookup:

  auto prev = std::prev(it);
  if (prev->key().equal(*_cache._schema, *_last_key->_key)) {
     it->set_continuous(true);

but handle_end_of_stream() is not invoked under allocating section.

Example of 2 can be found in mutation_cleaner_impl::merge_some() where
it does:

  return with_linearized_managed_bytes([&] {
  ...
    return _worker_state->alloc_section(region, [&] {

Fixes #6637.
Refs #6108.

Tests:

  - unit (all)

Message-Id: <1592218544-9435-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit e81fc1f095)
2020-06-21 11:58:59 +03:00
Yaron Kaikov
ec12331f11 release: prepare for 3.3.4 2020-06-15 21:19:02 +03:00
Avi Kivity
ccc463b5e5 tools: toolchain: regenerate for gnutls 3.6.14
CVE-2020-13777.

Fixes #6627.

Toolchain source image registry disambiguated due to tighter podman defaults.
2020-06-15 08:05:58 +03:00
Calle Wilund
4a9676f6b7 gms::inet_address: Fix sign extension error in custom address formatting
Fixes #5808

Seems some gcc:s will generate the code as sign extending. Mine does not,
but this should be more correct anyhow.

Added small stringify test to serialization_test for inet_address

(cherry picked from commit a14a28cdf4)
2020-06-09 20:16:50 +03:00
Takuya ASADA
aaf4989c31 aws: update enhanced networking supported instance list
Sync enhanced networking supported instance list to latest one.

Reference: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/enhanced-networking.html

Fixes #6540

(cherry picked from commit 969c4258cf)
2020-06-09 16:03:00 +03:00
Asias He
b29f954f20 gossip: Make is_safe_for_bootstrap more strict
Consider

1. Start n1, n2 in the cluster
2. Stop n2 and delete all data for n2
3. Start n2 to replace itself with replace_address_first_boot: n2
4. Kill n2 before n2 finishes the replace operation
5. Remove replace_address_first_boot: n2 from scylla.yaml of n2
6. Delete all data for n2
7. Start n2

At step 7, n2 will be allowed to bootstrap as a new node, because the
application state of n2 in the cluster is HIBERNATE which is not
rejected in the check of is_safe_for_bootstrap. As a result, n2 will
replace n2 with a different tokens and a different host_id, as if the
old n2 node was removed from the cluster silently.

Fixes #5172

(cherry picked from commit cdcedf5eb9)
2020-05-25 14:30:53 +03:00
Eliran Sinvani
5546d5df7b Auth: return correct error code when role is not found
Scylla returns the wrong error code (0000 - server internal error)
in response to trying to do authentication/authorization operations
that involves a non-existing role.
This commit changes those cases to return error code 2200 (invalid
query) which is the correct one and also the one that Cassandra
returns.
Tests:
    Unit tests (Dev)
    All auth and auth_role dtests

(cherry picked from commit ce8cebe34801f0ef0e327a32f37442b513ffc214)

Fixes #6363.
2020-05-25 12:58:38 +03:00
Amnon Heiman
541c29677f storage_service: get_range_to_address_map prevent use after free
The implementation of get_range_to_address_map has a default behaviour,
when getting an empty keypsace, it uses the first non-system keyspace
(first here is basically, just a keyspace).

The current implementation has two issues, first, it uses a reference to
a string that is held on a stack of another function. In other word,
there's a use after free that is not clear why we never hit.

The second, it calls get_non_system_keyspaces twice. Though this is not
a bug, it's redundant (get_non_system_keyspaces uses a loop, so calling
that function does have a cost).

This patch solves both issues, by chaning the implementation to hold a
string instead of a reference to a string.

Second, it stores the results from get_non_system_keyspaces and reuse
them it's more efficient and holds the returned values on the local
stack.

Fixes #6465

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
(cherry picked from commit 69a46d4179)
2020-05-25 12:48:48 +03:00
Hagit Segev
06f18108c0 release: prepare for 3.3.3 2020-05-24 23:28:07 +03:00
Tomasz Grabiec
90002ca3d2 sstables: index_reader: Fix overflow when calculating promoted index end
When index file is larger than 4GB, offset calculation will overflow
uint32_t and _promoted_index_end will be too small.

As a result, promoted_index_size calculation will underflow and the
rest of the page will be interpretd as a promoted index.

The partitions which are in the remainder of the index page will not
be found by single-partition queries.

Data is not lost.

Introduced in 6c5f8e0eda.

Fixes #6040
Message-Id: <20200521174822.8350-1-tgrabiec@scylladb.com>

(cherry picked from commit a6c87a7b9e)
2020-05-24 09:46:11 +03:00
Rafael Ávila de Espíndola
da23902311 repair: Make sure sinks are always closed
In a recent next failure I got the following backtrace

    function=function@entry=0x270360 "seastar::rpc::sink_impl<Serializer, Out>::~sink_impl() [with Serializer = netw::serializer; Out = {repair_row_on_wire_with_cmd}]") at assert.c:101
    at ./seastar/include/seastar/core/shared_ptr.hh:463
    at repair/row_level.cc:2059

This patch changes a few functions to use finally to make sure the sink
is always closed.

Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
Message-Id: <20200515202803.60020-1-espindola@scylladb.com>
(cherry picked from commit 311fbe2f0a)

Ref #6414
2020-05-20 09:00:57 +03:00
Asias He
2b0dc21f97 repair: Fix race between write_end_of_stream and apply_rows
Consider: n1, n2, n1 is the repair master, n2 is the repair follower.

=== Case 1 ===
1) n1 sends missing rows {r1, r2} to n2
2) n2 runs apply_rows_on_follower to apply rows, e.g., {r1, r2}, r1
   is written to sstable, r2 is not written yet, r1 belongs to
   partition 1, r2 belongs to partition 2. It yields after row r1 is
   written.
   data: partition_start, r1
3) n1 sends repair_row_level_stop to n2 because error has happened on n1
4) n2 calls wait_for_writer_done() which in turn calls write_end_of_stream()
   data: partition_start, r1, partition_end
5) Step 2 resumes to apply the rows.
   data: partition_start, r1, partition_end, partition_end, partition_start, r2

=== Case 2 ===
1) n1 sends missing rows {r1, r2} to n2
2) n2 runs apply_rows_on_follower to apply rows, e.g., {r1, r2}, r1
   is written to sstable, r2 is not written yet, r1 belongs to partition
   1, r2 belongs to partition 2. It yields after partition_start for r2
   is written but before _partition_opened is set to true.
   data: partition_start, r1, partition_end, partition_start
3) n1 sends repair_row_level_stop to n2 because error has happened on n1
4) n2 calls wait_for_writer_done() which in turn calls write_end_of_stream().
   Since _partition_opened[node_idx] is false, partition_end is skipped,
   end_of_stream is written.
   data: partition_start, r1, partition_end, partition_start, end_of_stream

This causes unbalanced partition_start and partition_end in the stream
written to sstables.

To fix, serialize the write_end_of_stream and apply_rows with a semaphore.

Fixes: #6394
Fixes: #6296
Fixes: #6414
(cherry picked from commit b2c4d9fdbc)
2020-05-20 08:22:05 +03:00
Piotr Dulikowski
b544691493 hinted handoff: don't keep positions of old hints in rps_set
When sending hints from one file, rps_set field in send_one_file_ctx
keeps track of commitlog positions of hints that are being currently
sent, or have failed to be sent. At the end of the operation, if sending
of some hints failed, we will choose position of the earliest hint that
failed to be sent, and will retry sending that file later, starting from
that position. This position is stored in _last_not_complete_rp.

Usually, this set has a bounded size, because we impose a limit of at
most 128 hints being sent concurrently. Because we do not attempt to
send any more hints after a failure is detected, rps_set should not have
more than 128 elements at a time.

Due to a bug, commitlog positions of old hints (older than
gc_grace_seconds of the destination table) were inserted into rps_set
but not removed after checking their age. This could cause rps_set to
grow very large when replaying a file with old hints.

Moreover, if the file mixed expired and non-expired hints (which could
happen if it had hints to two tables with different gc_grace_seconds),
and sending of some non-expired hints failed, then positions of expired
hints could influence calculation _last_not_complete_rp, and more hints
than necessary would be resent on the next retry.

This simple patch removes commitlog position of a hint from rps_set when
it is detected to be too old.

Fixes #6422

(cherry picked from commit 85d5c3d5ee)
2020-05-20 08:06:17 +03:00
Piotr Dulikowski
d420b06844 hinted handoff: remove discarded hint positions from rps_set
Related commit: 85d5c3d

When attempting to send a hint, an exception might occur that results in
that hint being discarded (e.g. keyspace or table of the hint was
removed).

When such an exception is thrown, position of the hint will already be
stored in rps_set. We are only allowed to retain positions of hints that
failed to be sent and needed to be retried later. Dropping a hint is not
an error, therefore its position should be removed from rps_set - but
current logic does not do that.

Because of that bug, hint files with many discardable hints might cause
rps_set to grow large when the file is replayed. Furthermore, leaving
positions of such hints in rps_set might cause more hints than necessary
to be re-sent if some non-discarded hints fail to be sent.

This commit fixes the problem by removing positions of discarded hints
from rps_set.

Fixes #6433

(cherry picked from commit 0c5ac0da98)
2020-05-20 08:04:10 +03:00
Avi Kivity
b3a2cb2f68 Update seastar submodule
* seastar 0ebd89a858...30f03aeba9 (1):
  > timer: add scheduling_group awareness

Fixes #6170.
2020-05-10 18:39:20 +03:00
Hagit Segev
c8c057f5f8 release: prepare for 3.3.2 2020-05-10 18:16:28 +03:00
Gleb Natapov
038bfc925c storage_proxy: limit read repair only to replicas that answered during speculative reads
Speculative reader has more targets that needed for CL. In case there is
a digest mismatch the repair runs between all of them, but that violates
provided CL. The patch makes it so that repair runs only between
replicas that answered (there will be CL of them).

Fixes #6123

Reviewed-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20200402132245.GA21956@scylladb.com>
(cherry picked from commit 36a24bbb70)
2020-05-07 19:48:37 +03:00
Mike Goltsov
13a4e7db83 fix error in fstrim service (scylla_util.py)
On Centos 7 machine:

fstrim.timer not enabled, only unmasked due scylla_fstrim_setup on installation
When trying run scylla-fstrim service manually you get error:

Traceback (most recent call last):
File "/opt/scylladb/scripts/libexec/scylla_fstrim", line 60, in <module>
main()
File "/opt/scylladb/scripts/libexec/scylla_fstrim", line 44, in main
cfg = parse_scylla_dirs_with_default(conf=args.config)
File "/opt/scylladb/scripts/scylla_util.py", line 484, in parse_scylla_dirs_with_default
if key not in y or not y[k]:
NameError: name 'k' is not defined

It caused by error in scylla_util.py

Fixes #6294.

(cherry picked from commit 068bb3a5bf)
2020-05-07 19:45:50 +03:00
Juliusz Stasiewicz
727d6cf8f3 atomic_cell: special rule for printing counter cells
Until now, attempts to print counter update cell would end up
calling abort() because `atomic_cell_view::value()` has no
specialized visitor for `imr::pod<int64_t>::basic_view<is_mutable>`,
i.e. counter update IMR type. Such visitor is not easy to write
if we want to intercept counters only (and not all int64_t values).

Anyway, linearized byte representation of counter cell would not
be helpful without knowing if it consists of counter shards or
counter update (delta) - and this must be known upon `deserialize`.

This commit introduces simple approach: it determines cell type on
high level (from `atomic_cell_view`) and prints counter contents by
`counter_cell_view` or `atomic_cell_view::counter_update_value()`.

Fixes #5616

(cherry picked from commit 0ea17216fe)
2020-05-07 19:40:47 +03:00
Tomasz Grabiec
6d6d7b4abe sstables: Release reserved space for sharding metadata
The intention of the code was to clear sharding metadata
chunked_vector so that it doesn't bloat memory.

The type of c is `chunked_vector*`. Assigning `{}`
clears the pointer while the intended behavior was to reset the
`chunked_vector` instance. The original instance is left unmodified
with all its reserved space.

Because of this, the previous fix had no effect because token ranges
are stored entirely inline and popping them doesn't realease memory.

Fixes #4951

Tests:
  - sstable_mutation_test (dev)
  - manual using scylla binary on customer data on top of 2019.1.5

Reviewed-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <1584559892-27653-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 5fe626a887)
2020-05-07 19:06:22 +03:00
Tomasz Grabiec
28f974b810 Merge "Don't return stale data by properly invalidating row cache after cleanup" from Raphael
Row cache needs to be invalidated whenever data in sstables
changes. Cleanup removes data from sstables which doesn't belong to
the node anymore, which means cache must be invalidated on cleanup.
Currently, stale data can be returned when a node re-owns ranges which
data are still stored in the node's row cache, because cleanup didn't
invalidate the cache."

Fixes #4446.

tests:
- unit tests (dev mode)
- dtests:
    update_cluster_layout_tests.py:TestUpdateClusterLayout.simple_decommission_node_2_test
    cleanup_test.py

(cherry picked from commit d0b6be0820)
2020-05-07 16:24:51 +03:00
Piotr Sarna
5fdadcaf3b network_topology_strategy: validate integers
In order to prevent users from creating a network topology
strategy instance with invalid inputs, it's not enough to use
std::stol() on the input: a string "3abc" still returns the number '3',
but will later confuse cqlsh and other drivers, when they ask for
topology strategy details.
The error message is now more human readable, since for incorrect
numeric inputs it used to return a rather cryptic message:
    ServerError: stol()
This commit fixes the issue and comes with a simple test.

Fixes #3801
Tests: unit(dev)
Message-Id: <7aaae83d003738f047d28727430ca0a5cec6b9c6.1583478000.git.sarna@scylladb.com>

(cherry picked from commit 5b7a35e02b)
2020-05-07 16:24:49 +03:00
Pekka Enberg
a960394f27 scripts/jobs: Keep memory reserve when calculating parallelism
The "jobs" script is used to determine the amount of compilation
parallelism on a machine. It attempts to ensure each GCC process has at
least 4 GB of memory per core. However, in the worst case scenario, we
could end up having the GCC processes take up all the system memory,
forcin swapping or OOM killer to kick in. For example, on a 4 core
machine with 16 GB of memory, this worst case scenario seems easy to
trigger in practice.

Fix up the problem by keeping a 1 GB of memory reserve for other
processes and calculating parallelism based on that.

Message-Id: <20200423082753.31162-1-penberg@scylladb.com>
(cherry picked from commit 7304a795e5)
2020-05-04 19:01:54 +03:00
Piotr Sarna
3216a1a70a alternator: fix signature timestamps
Generating timestamps for auth signatures used a non-thread-safe
::gmtime function instead of thread-safe ::gmtime_r.

Tests: unit(dev)
Fixes #6345

(cherry picked from commit fb7fa7f442)
2020-05-04 17:08:13 +03:00
Avi Kivity
5a7fd41618 Merge 'Fix hang in multishard_writer' from Asias
"
This series fix hang in multishard_writer when error happens. It contains
- multishard_writer: Abort the queue attached to consumers when producer fails
- repair: Fix hang when the writer is dead

Fixes #6241
Refs: #6248
"

* asias-stream_fix_multishard_writer_hang:
  repair: Fix hang when the writer is dead
  mutation_writer_test: Add test_multishard_writer_producer_aborts
  multishard_writer: Abort the queue attached to consumers when producer fails

(cherry picked from commit 8925e00e96)
2020-05-01 20:13:00 +03:00
Raphael S. Carvalho
dd24ba7a62 api/service: fix segfault when taking a snapshot without keyspace specified
If no keyspace is specified when taking snapshot, there will be a segfault
because keynames is unconditionally dereferenced. Let's return an error
because a keyspace must be specified when column families are specified.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20200427195634.99940-1-raphaelsc@scylladb.com>
(cherry picked from commit 02e046608f)

Fixes #6336.
2020-04-30 12:57:14 +03:00
Avi Kivity
204f6dd393 Update seastar submodule
* seastar a0bdc6cd85...0ebd89a858 (1):
  > http server: fix "Date" header format

Fixes #6253.
2020-04-26 19:31:44 +03:00
Nadav Har'El
b1278adc15 alternator: unzero "scylla_alternator_total_operations" metric
In commit 388b492040, which was only supposed
to move around code, we accidentally lost the line which does

    _executor.local()._stats.total_operations++;

So after this commit this counter was always zero...
This patch returns the line incrementing this counter.

Arguably, this counter is not very important - a user can also calculate
this number by summing up all the counters in the scylla_alternator_operation
array (these are counters for individual types of operations). Nevertheless,
as long as we do export a "scylla_alternator_total_operations" metric,
we need to correctly calculate it and can't leave it zero :-)

Fixes #5836

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20200219162820.14205-1-nyh@scylladb.com>
(cherry picked from commit b8aed18a24)
2020-04-19 19:07:31 +03:00
Botond Dénes
ee9677ef71 schema: schema(): use std::stable_sort() to sort key columns
When multiple key columns (clustering or partition) are passed to
the schema constructor, all having the same column id, the expectation
is that these columns will retain the order in which they were passed to
`schema_builder::with_column()`. Currently however this is not
guaranteed as the schema constructor sort key columns by column id with
`std::sort()`, which doesn't guarantee that equally comparing elements
retain their order. This can be an issue for indexes, the schemas of
which are built independently on each node. If there is any room for
variance between for the key column order, this can result in different
nodes having incompatible schemas for the same index.
The fix is to use `std::stable_sort()` which guarantees that the order
of equally comparing elements won't change.

This is a suspected cause of #5856, although we don't have hard proof.

Fixes: #5856
Signed-off-by: Botond Dénes <bdenes@scylladb.com>
[avi: upgraded "Refs" to "Fixes", since we saw that std::sort() becomes
      unstable at 17 elements, and the failing schema had a
      clustering key with 23 elements]
Message-Id: <20200417121848.1456817-1-bdenes@scylladb.com>
(cherry picked from commit a4aa753f0f)
2020-04-19 18:19:05 +03:00
Nadav Har'El
2060e361cf materialized views: fix corner case of view updates used by Alternator
While CQL does not allow creation of a materialized view with more than one
base regular column in the view's key, in Alternator we do allow this - both
partition and clustering key may be a base regular column. We had a bug in
the logic handling this case:

If the new base row is missing a value for *one* of the view key columns,
we shouldn't create a view row. Similarly, if the existing base row was
missing a value for *one* of the view key columns, a view row does not
exist and doesn't need to be deleted.  This was done incorrectly, and made
decisions based on just one of the key columns, and the logic is now
fixed (and I think, simplified) in this patch.

With this patch, the Alternator test which previously failed because of
this problem now passes. The patch also includes new tests in the existing
C++ unit test test_view_with_two_regular_base_columns_in_key. This tests
was already supposed to be testing various cases of two-new-key-columns
updates, but missed the cases explained above. These new tests failed
badly before this patch - some of them had clean write errors, others
caused crashes. With this patch, they pass.

Fixes #6008.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20200312162503.8944-1-nyh@scylladb.com>
(cherry picked from commit 635e6d887c)
2020-04-19 15:24:19 +03:00
Hagit Segev
6f939ffe19 release: prepare for 3.3.1 2020-04-18 00:23:31 +03:00
Kamil Braun
69105bde8a sstables: freeze types nested in collection types in legacy sstables
Some legacy `mc` SSTables (created in Scylla 3.0) may contain incorrect
serialization headers, which don't wrap frozen UDTs nested inside collections
with the FrozenType<...> tag. When reading such SSTable,
Scylla would detect a mismatch between the schema saved in schema
tables (which correctly wraps UDTs in the FrozenType<...> tag) and the schema
from the serialization header (which doesn't have these tags).

SSTables created in Scylla versions 3.1 and above, in particular in
Scylla versions that contain this commit, create correct serialization
headers (which wrap UDTs in the FrozenType<...> tag).

This commit does two things:
1. for all SSTables created after this commit, include a new feature
   flag, CorrectUDTsInCollections, presence of which implies that frozen
   UDTs inside collections have the FrozenType<...> tag.
2. when reading a Scylla SSTable without the feature flag, we assume that UDTs
   nested inside collections are always frozen, even if they don't have
   the tag. This assumption is safe to be made, because at the time of
   this commit, Scylla does not allow non-frozen (multi-cell) types inside
   collections or UDTs, and because of point 1 above.

There is one edge case not covered: if we don't know whether the SSTable
comes from Scylla or from C*. In that case we won't make the assumption
described in 2. Therefore, if we get a mismatch between schema and
serialization headers of a table which we couldn't confirm to come from
Scylla, we will still reject the table. If any user encounters such an
issue (unlikely), we will have to use another solution, e.g. using a
separate tool to rewrite the SSTable.

Fixes #6130.

(cherry picked from commit 3d811e2f95)
2020-04-17 09:12:28 +03:00
Kamil Braun
e09e9a5929 sstables: move definition of column_translation::state::build to a .cc file
Ref #6130
2020-04-17 09:12:28 +03:00
Piotr Sarna
2308bdbccb alternator: use partition tombstone if there's no clustering key
As @tgrabiec helpfully pointed out, creating a row tombstone
for a table which does not have a clustering key in its schema
creates something that looks like an open-ended range tombstone.
That's problematic for KA/LA sstable formats, which are incapable
of writing such tombstones, so a workaround is provided
in order to allow using KA/LA in alternator.

Fixes #6035
Cherry-picked from 0a2d7addc0
2020-04-16 12:14:10 +02:00
Asias He
a2d39c9a2e gossip: Add an option to force gossip generation
Consider 3 nodes in the cluster, n1, n2, n3 with gossip generation
number g1, g2, g3.

n1, n2, n3 running scylla version with commit
0a52ecb6df (gossip: Fix max generation
drift measure)

One year later, user wants the upgrade n1,n2,n3 to a new version

when n3 does a rolling restart with a new version, n3 will use a
generation number g3'. Because g3' - g2 > MAX_GENERATION_DIFFERENCE and
g3' - g1 > MAX_GENERATION_DIFFERENCE, so g1 and g2 will reject n3's
gossip update and mark g3 as down.

Such unnecessary marking of node down can cause availability issues.
For example:

DC1: n1, n2
DC2: n3, n4

When n3 and n4 restart, n1 and n2 will mark n3 and n4 as down, which
causes the whole DC2 to be unavailable.

To fix, we can start the node with a gossip generation within
MAX_GENERATION_DIFFERENCE difference for the new node.

Once all the nodes run the version with commit
0a52ecb6df, the option is no logger
needed.

Fixes #5164

(cherry picked from commit 743b529c2b)
2020-03-27 12:49:23 +01:00
Asias He
5fe2ce3bbe gossiper: Always use the new generation number
User reported an issue that after a node restart, the restarted node
is marked as DOWN by other nodes in the cluster while the node is up
and running normally.

Consier the following:

- n1, n2, n3 in the cluster
- n3 shutdown itself
- n3 send shutdown verb to n1 and n2
- n1 and n2 set n3 in SHUTDOWN status and force the heartbeat version to
  INT_MAX
- n3 restarts
- n3 sends gossip shadow rounds to n1 and n2, in
  storage_service::prepare_to_join,
- n3 receives response from n1, in gossiper::handle_ack_msg, since
  _enabled = false and _in_shadow_round == false, n3 will apply the
  application state in fiber1, filber 1 finishes faster filber 2, it
  sets _in_shadow_round = false
- n3 receives response from n2, in gossiper::handle_ack_msg, since
  _enabled = false and _in_shadow_round == false, n3 will apply the
  application state in fiber2, filber 2 yields
- n3 finishes the shadow round and continues
- n3 resets gossip endpoint_state_map with
  gossiper.reset_endpoint_state_map()
- n3 resumes fiber 2, apply application state about n3 into
  endpoint_state_map, at this point endpoint_state_map contains
  information including n3 itself from n2.
- n3 calls gossiper.start_gossiping(generation_number, app_states, ...)
  with new generation number generated correctly in
  storage_service::prepare_to_join, but in
  maybe_initialize_local_state(generation_nbr), it will not set new
  generation and heartbeat if the endpoint_state_map contains itself
- n3 continues with the old generation and heartbeat learned in fiber 2
- n3 continues the gossip loop, in gossiper::run,
  hbs.update_heart_beat() the heartbeat is set to the number starting
  from 0.
- n1 and n2 will not get update from n3 because they use the same
  generation number but n1 and n2 has larger heartbeat version
- n1 and n2 will mark n3 as down even if n3 is alive.

To fix, always use the the new generation number.

Fixes: #5800
Backports: 3.0 3.1 3.2
(cherry picked from commit 62774ff882)
2020-03-27 12:49:20 +01:00
Piotr Sarna
aafa34bbad cql: fix qualifying indexed columns for filtering
When qualifying columns to be fetched for filtering, we also check
if the target column is not used as an index - in which case there's
no need of fetching it. However, the check was incorrectly assuming
that any restriction is eligible for indexing, while it's currently
only true for EQ. The fix makes a more specific check and contains
many dynamic casts, but these will hopefully we gone once our
long planned "restrictions rewrite" is done.
This commit comes with a test.

Fixes #5708
Tests: unit(dev)

(cherry picked from commit 767ff59418)
2020-03-22 09:00:51 +01:00
Hagit Segev
7ae2cdf46c release: prepare for 3.3.0 2020-03-19 21:46:44 +02:00
Hagit Segev
863f88c067 release: prepare for 3.3.rc3 2020-03-15 22:45:30 +02:00
Avi Kivity
90b4e9e595 Update seastar submodule
* seastar f54084c08f...a0bdc6cd85 (1):
  > tls: Fix race and stale memory use in delayed shutdown

Fixes #5759 (maybe)
2020-03-12 19:41:50 +02:00
Konstantin Osipov
434ad4548f locator: correctly select endpoints if RF=0
SimpleStrategy creates a list of endpoints by iterating over the set of
all configured endpoints for the given token, until we reach keyspace
replication factor.
There is a trivial coding bug when we first add at least one endpoint
to the list, and then compare list size and replication factor.
If RF=0 this never yields true.
Fix by moving the RF check before at least one endpoint is added to the
list.
Cassandra never had this bug since it uses a less fancy while()
loop.

Fixes #5962
Message-Id: <20200306193729.130266-1-kostja@scylladb.com>

(cherry picked from commit ac6f64a885)
2020-03-12 12:09:46 +02:00
Avi Kivity
cbbb15af5c logalloc: increase capacity of _regions vector outside reclaim lock
Reclaim consults the _regions vector, so we don't want it moving around while
allocating more capacity. For that we take the reclaim lock. However, that
can cause a false-positive OOM during startup:

1. all memory is allocated to LSA as part of priming (2baa16b371)
2. the _regions vector is resized from 64k to 128k, requiring a segment
   to be freed (plenty are free)
3. but reclaiming_lock is taken, so we cannot reclaim anything.

To fix, resize the _regions vector outside the lock.

Fixes #6003.
Message-Id: <20200311091217.1112081-1-avi@scylladb.com>

(cherry picked from commit c020b4e5e2)
2020-03-12 11:25:20 +02:00
Benny Halevy
3231580c05 dist/redhat: scylla.spec.mustache: set _no_recompute_build_ids
By default, `/usr/lib/rpm/find-debuginfo.sh` will temper with
the binary's build-id when stripping its debug info as it is passed
the `--build-id-seed <version>.<release>` option.

To prevent that we need to set the following macros as follows:
  unset `_unique_build_ids`
  set `_no_recompute_build_ids` to 1

Fixes #5881

Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
(cherry picked from commit 25a763a187)
2020-03-09 15:21:50 +02:00
Piotr Sarna
62364d9dcd Merge 'cql3: do_execute_base_query: fix null deref ...
... when clustering key is unavailable' from Benny

This series fixes null pointer dereference seen in #5794

efd7efe cql3: generate_base_key_from_index_pk; support optional index_ck
7af1f9e cql3: do_execute_base_query: generate open-ended slice when clustering key is unavailable
7fe1a9e cql3: do_execute_base_query: fixup indentation

Fixes #5794

Branches: 3.3

Test: unit(dev) secondary_indexes_test:TestSecondaryIndexes.test_truncate_base(debug)

* bhalevy/fix-5794-generate_base_key_from_index_pk:
  cql3: do_execute_base_query: fixup indentation
  cql3: do_execute_base_query: generate open-ended slice when clustering key is unavailable
  cql3: generate_base_key_from_index_pk; support optional index_ck

(cherry picked from commit 4e95b67501)
2020-03-09 15:20:01 +02:00
Takuya ASADA
3bed8063f6 dist/debian: fix "unable to open node-exporter.service.dpkg-new" error
It seems like *.service is conflicting on install time because the file
installed twice, both debian/*.service and debian/scylla-server.install.

We don't need to use *.install, so we can just drop the line.

Fixes #5640

(cherry picked from commit 29285b28e2)
2020-03-03 12:40:39 +02:00
Yaron Kaikov
413fcab833 release: prepare for 3.3.rc2 2020-02-27 14:45:18 +02:00
Juliusz Stasiewicz
9f3c3036bf cdc: set TTLs on CDC log cells
Cells in CDC logs used to be created while completely neglecting
TTLs (the TTLs from `cdc = {...'ttl':600}`). This patch adds TTLs
to all cells; there are no row markers, so wee need not set TTL
there.

Fixes #5688

(cherry picked from commit 67b92c584f)
2020-02-26 18:12:55 +02:00
Benny Halevy
ff2e108a6d gossiper: do_stop_gossiping: copy live endpoints vector
It can be resized asynchronously by mark_dead.

Fixes #5701

Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Message-Id: <20200203091344.229518-1-bhalevy@scylladb.com>
(cherry picked from commit f45fabab73)
2020-02-26 13:00:11 +02:00
Gleb Natapov
ade788ffe8 commitlog: use commitlog IO scheduling class for segment zeroing
There may be other commitlog writes waiting for zeroing to complete, so
not using proper scheduling class causes priority inversion.

Fixes #5858.

Message-Id: <20200220102939.30769-2-gleb@scylladb.com>
(cherry picked from commit 6a78cc9e31)
2020-02-26 12:51:10 +02:00
Benny Halevy
1f8bb754d9 storage_service: drain_on_shutdown: unregister storage_proxy subscribers from local_storage_service
Match subscription done in main() and avoid cross shard access
to _lifecycle_subscribers vector.

Fixes #5385

Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Acked-by: Pavel Emelyanov <xemul@scylladb.com>
Message-Id: <20200123092817.454271-1-bhalevy@scylladb.com>
(cherry picked from commit 5b0ea4c114)
2020-02-25 16:39:49 +02:00
Tomasz Grabiec
7b2eb09225 Merge fixes for use-after-frees related to shutdown of services
Backport of 884d5e2bcb and
4839ca8491.

Fixes crashes when scylla is stopped early during boot.

Merged from https://github.com/xemul/scylla/tree/br-mm-combined-fixes-for-3.3

Fixes #5765.
2020-02-25 13:34:01 +01:00
Pavel Emelyanov
d2293f9fd5 migration_manager: Abort and wait cluster upgrade waiters
The maybe_schedule_schema_pull waits for schema_tables_v3 to
become available. This is unsafe in case migration manager
goes away before the feature is enabled.

Fix this by subscribing on feature with feature::listener and
waiting for condition variable in maybe_schedule_schema_pull.

Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
2020-02-24 14:18:15 +03:00
Pavel Emelyanov
25b31f6c23 migration_manager: Abort and wait delayed schema pulls
The sleep is interrupted with the abort source, the "wait" part
is done with the existing _background_tasks gate. Also we need
to make sure the gate stays alive till the end of the function,
so make use of the async_sharded_service (migration manager is
already such).

Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
2020-02-24 14:18:15 +03:00
Pavel Emelyanov
742a1ce7d6 storage_service: Unregister from gossiper notifications ... at all
This unregistration doesn't happen currently, but doesn't seem to
cause any problems in general, as on stop gossiper is stopped and
nothing from it hits the store_service.

However (!) if an exception pops up between the storage_service
is subscribed on gossiper and the drain_on_shutdown defer action
is set up  then we _may_ get into the following situation:

- main's stuff gets unrolled back
- gossiper is not stopped (drain_on_shutdown defer is not set up)
- migration manager is stopped (with deferred action in main)
- a nitification comes from gossiper
    -> storage_service::on_change might want to pull schema with
       the help of local migration manager
    -> assert(local_is_initialized) strikes

Fix this by registering storage_service to gossiper a bit earlier
(both are already initialized y that time) and setting up unregister
defer right afterwards.

Test: unit(dev), manual start-stop
Bug: #5628

Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Message-Id: <20200130190343.25656-1-xemul@scylladb.com>
2020-02-24 14:18:15 +03:00
Avi Kivity
4ca9d23b83 Revert "streaming: Do not invalidate cache if no sstable is added in flush_streaming_mutations"
This reverts commit bdc542143e. Exposes a data resurrection
bug (#5838).
2020-02-24 10:02:58 +02:00
Avi Kivity
9e97f3a9b3 Update seastar submodule
* seastar dd686552ff...f54084c08f (2):
  > reactor: fallback to epoll backend when fs.aio-max-nr is too small
  > util: move read_sys_file_as() from iotune to seastar header, rename read_first_line_as()

Fixes #5638.
2020-02-20 10:25:00 +02:00
Piotr Dulikowski
183418f228 hh: handle counter update hints correctly
This patch fixes a bug that appears because of an incorrect interaction
between counters and hinted handoff.

When a counter is updated on the leader, it sends mutations to other
replicas that contain all counter shards from the leader. If consistency
level is achieved but some replicas are unavailable, a hint with
mutation containing counter shards is stored.

When a hint's destination node is no longer its replica, it is attempted
to be sent to all its current replicas. Previously,
storage_proxy::mutate was used for that purpose. It was incorrect
because that function treats mutations for counter tables as mutations
containing only a delta (by how much to increase/decrease the counter).
These two types of mutations have different serialization format, so in
this case a "shards" mutation is reinterpreted as "delta" mutation,
which can cause data corruption to occur.

This patch backports `storage_proxy::mutate_hint_from_scratch`
function, which bypasses special handling of counter mutations and
treats them as regular mutations - which is the correct behavior for
"shards" mutations.

Refs #5833.
Backports: 3.1, 3.2, 3.3
Tests: unit(dev)
(cherry picked from commit ec513acc49)
2020-02-19 16:49:12 +02:00
Piotr Sarna
756574d094 db,view: fix generating view updates for partition tombstones
The update generation path must track and apply all tombstones,
both from the existing base row (if read-before-write was needed)
and for the new row. One such path contained an error, because
it assumed that if the existing row is empty, then the update
can be simply generated from the new row. However, lack of the
existing row can also be the result of a partition/range tombstone.
If that's the case, it needs to be applied, because it's entirely
possible that this partition row also hides the new row.
Without taking the partition tombstone into account, creating
a future tombstone and inserting an out-of-order write before it
in the base table can result in ghost rows in the view table.
This patch comes with a test which was proven to fail before the
changes.

Branches 3.1,3.2,3.3
Fixes #5793

Tests: unit(dev)
Message-Id: <8d3b2abad31572668693ab585f37f4af5bb7577a.1581525398.git.sarna@scylladb.com>
(cherry picked from commit e93c54e837)
2020-02-16 20:26:28 +02:00
Rafael Ávila de Espíndola
a348418918 service: Add a lock around migration_notifier::_listeners
Before this patch the iterations over migration_notifier::_listeners
could race with listeners being added and removed.

The addition side is not modified, since it is common to add a
listener during construction and it would require a fairly big
refactoring. Instead, the iteration is modified to use indexes instead
of iterators so that it is still valid if another listener is added
concurrently.

For removal we use a rw lock, since removing an element invalidates
indexes too. There are only a few places that needed refactoring to
handle unregister_listener returning a future<>, so this is probably
OK.

Fixes #5541.

Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
Message-Id: <20200120192819.136305-1-espindola@scylladb.com>
(cherry picked from commit 27bd3fe203)
2020-02-16 20:13:42 +02:00
Avi Kivity
06c0bd0681 Update seastar submodule
* seastar 3f3e117de3...dd686552ff (1):
  > perftune.py: Use safe_load() for fix arbitrary code execution

Fixes #5630.
2020-02-16 15:53:16 +02:00
Avi Kivity
223c300435 Point seastar submodule at scylla-seastar.git branch-3.3
This allows us to backport seastar patches to Scylla 3.3.
2020-02-16 15:51:46 +02:00
Gleb Natapov
ac8bef6781 commitlog: fix flushing an entry marked as "sync" in periodic mode
After 546556b71b we can have mixed writes into commitlog,
some do flush immediately some do not. If non flushing write races with
flushing one and becomes responsible for writing back its buffer into a
file flush will be skipped which will cause assert in batch_cycle() to
trigger since flush position will not be advanced. Fix that by checking
that flush was skipped and in this case flush explicitly our file
position.

Fixes #5670

Message-Id: <20200128145103.GI26048@scylladb.com>
(cherry picked from commit c654ffe34b)
2020-02-16 15:48:40 +02:00
Pavel Solodovnikov
68691907af lwt: fix handling of nulls in parameter markers for LWT queries
This patch affects the LWT queries with IF conditions of the
following form: `IF col in :value`, i.e. if the parameter
marker is used.

When executing a prepared query with a bound value
of `(None,)` (tuple with null, example for Python driver), it is
serialized not as NULL but as "empty" value (serialization
format differs in each case).

Therefore, Scylla deserializes the parameters in the request as
empty `data_value` instances, which are, in turn, translated
to non-empty `bytes_opt` with empty byte-string value later.

Account for this case too in the CAS condition evaluation code.

Example of a problem this patch aims to fix:

Suppose we have a table `tbl` with a boolean field `test` and
INSERT a row with NULL value for the `test` column.

Then the following update query fails to apply due to the
error in IF condition evaluation code (assume `v=(null)`):
`UPDATE tbl SET test=false WHERE key=0 IF test IN :v`
returns false in `[applied]` column, but is expected to succeed.

Tests: unit(debug, dev), dtest(prepared stmt LWT tests at https://github.com/scylladb/scylla-dtest/pull/1286)

Fixes: #5710

Signed-off-by: Pavel Solodovnikov <pa.solodovnikov@scylladb.com>
Message-Id: <20200205102039.35851-1-pa.solodovnikov@scylladb.com>
(cherry picked from commit bcc4647552)
2020-02-16 15:29:28 +02:00
Avi Kivity
f59d2fcbf1 Merge "stop passing tracing state pointer in client_state" from Gleb
"
client_state is used simultaneously by many requests running in parallel
while tracing state pointer is per request. Both those facts do not sit
well together and as a result sometimes tracing state is being overwritten
while still been used by active request which may cause incorrect trace
or even a crash.
"

Fixes #5700.

Backported from 9f1f60fc38

* 'gleb/trace_fix_3.3_backport' of ssh://github.com/scylladb/seastar-dev:
  client_state: drop the pointer to a tracing state from client_state
  transport: pass tracing state explicitly instead of relying on it been in the client_state
  alternator: pass tracing state explicitly instead of relying on it been in the client_state
2020-02-16 15:23:41 +02:00
Asias He
bdc542143e streaming: Do not invalidate cache if no sstable is added in flush_streaming_mutations
The table::flush_streaming_mutations is used in the days when streaming
data goes to memtable. After switching to the new streaming, data goes
to sstables directly in streaming, so the sstables generated in
table::flush_streaming_mutations will be empty.

It is unnecessary to invalidate the cache if no sstables are added. To
avoid unnecessary cache invalidating which pokes hole in the cache, skip
calling _cache.invalidate() if the sstables is empty.

The steps are:

- STREAM_MUTATION_DONE verb is sent when streaming is done with old or
  new streaming
- table::flush_streaming_mutations is called in the verb handler
- cache is invalidated for the streaming ranges

In summary, this patch will avoid a lot of cache invalidation for
streaming.

Backports: 3.0 3.1 3.2
Fixes: #5769
(cherry picked from commit 5e9925b9f0)
2020-02-16 15:16:24 +02:00
Botond Dénes
061a02237c row: append(): downgrade assert to on_internal_error()
This assert, added by 060e3f8 is supposed to make sure the invariant of
the append() is respected, in order to prevent building an invalid row.
The assert however proved to be too harsh, as it converts any bug
causing out-of-order clustering rows into cluster unavailability.
Downgrade it to on_internal_error(). This will still prevent corrupt
data from spreading in the cluster, without the unavailability caused by
the assert.

Fixes: #5786
Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <20200211083829.915031-1-bdenes@scylladb.com>
(cherry picked from commit 3164456108)
2020-02-16 15:12:46 +02:00
Gleb Natapov
35b6505517 client_state: drop the pointer to a tracing state from client_state
client_state is shared between requests and tracing state is per
request. It is not safe to use the former as a container for the later
since a state can be overwritten prematurely by subsequent requests.

(cherry picked from commit 31cf2434d6)
2020-02-13 13:45:56 +02:00
Gleb Natapov
866c04dd64 transport: pass tracing state explicitly instead of relying on it been in the client_state
Multiple requests can use the same client_state simultaneously, so it is
not safe to use it as a container for a tracing state which is per request.
Currently next request may overwrite tracing state for previous one
causing, in a best case, wrong trace to be taken or crash if overwritten
pointer is freed prematurely.

Fixes #5700

(cherry picked from commit 9f1f60fc38)
2020-02-13 13:45:56 +02:00
Gleb Natapov
dc588e6e7b alternator: pass tracing state explicitly instead of relying on it been in the client_state
Multiple requests can use the same client_state simultaneously, so it is
not safe to use it as a container for a tracing state which is per
request. This is not yet an issue for the alternator since it creates
new client_state object for each request, but first of all it should not
and second trace state will be dropped from the client_state, by later
patch.

(cherry picked from commit 38fcab3db4)
2020-02-13 13:45:56 +02:00
Takuya ASADA
f842154453 dist/debian: keep /etc/systemd .conf files on 'remove'
Since dpkg does not re-install conffiles when it removed by user,
currently we are missing dependencies.conf and sysconfdir.conf on rollback.
To prevent this, we need to stop running
'rm -rf /etc/systemd/system/scylla-server.service.d/' on 'remove'.

Fixes #5734

(cherry picked from commit 43097854a5)
2020-02-12 14:26:40 +02:00
Yaron Kaikov
b38193f71d dist/docker: Switch to 3.3 release repository (#5756)
Change the SCYLLA_REPO_URL variable to point to branch-3.3 instead of
master. This ensures that Docker image builds that don't specify the
variable build from the right repository by default.
2020-02-10 11:11:38 +02:00
Rafael Ávila de Espíndola
f47ba6dc06 lua: Handle nil returns correctly
This is a minimum backport to 3.3.

With this patch lua nil values are mapped to CQL null values instead
of producing an error.

Fixes #5667

Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
Message-Id: <20200203164918.70450-1-espindola@scylladb.com>
2020-02-09 18:55:42 +02:00
Hagit Segev
0d0c1d4318 release: prepare for 3.3.rc1 2020-02-09 15:55:24 +02:00
Takuya ASADA
9225b17b99 scylla_post_install.sh: fix 'integer expression expected' error
awk returns float value on Debian, it causes postinst script failure
since we compare it as integer value.
Replaced with sed + bash.

Fixes #5569

(cherry picked from commit 5627888b7c)
2020-02-04 14:30:04 +02:00
Gleb Natapov
00b3f28199 db/system_keyspace: use user memory limits for local.paxos table
Treat writes to local.paxos as user memory, as the number of writes is
dependent on the amount of user data written with LWT.

Fixes #5682

Message-Id: <20200130150048.GW26048@scylladb.com>
(cherry picked from commit b08679e1d3)
2020-02-02 17:36:52 +02:00
Rafael Ávila de Espíndola
1bbe619689 types: Fix encoding of negative varint
We would sometimes produce an unnecessary extra 0xff prefix byte.

The new encoding matches what cassandra does.

This was both a efficiency and correctness issue, as using varint in a
key could produce different tokens.

Fixes #5656

Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
(cherry picked from commit c89c90d07f)
2020-02-02 16:00:58 +02:00
Avi Kivity
c36f71c783 test: make eventually() more patient
We use eventually() in tests to wait for eventually consistent data
to become consistent. However, we see spurious failures indicating
that we wait too little.

Increasing the timeout has a negative side effect in that tests that
fail will now take longer to do so. However, this negative side effect
is negligible to false-positive failures, since they throw away large
test efforts and sometimes require a person to investigate the problem,
only to conclude it is a false positive.

This patch therefore makes eventually() more patient, by a factor of
32.

Fixes #4707.
Message-Id: <20200130162745.45569-1-avi@scylladb.com>

(cherry picked from commit ec5b721db7)
2020-02-01 13:20:22 +02:00
Pekka Enberg
f5471d268b release: prepare for 3.3.rc0 2020-01-30 14:00:51 +02:00
Takuya ASADA
fd5c65d9dc dist/debian: Use tilde for release candidate builds
We need to add '~' to handle rcX version correctly on Debian variants
(merged at ae33e9f), but when we moved to relocated package we mistakenly
dropped the code, so add the code again.

Fixes #5641

(cherry picked from commit dd81fd3454)
2020-01-28 18:34:48 +02:00
Avi Kivity
3aa406bf00 tools: toolchain: dbuild: relax process limit in container
Docker restricts the number of processes in a container to some
limit it calculates. This limit turns out to be too low on large
machines, since we run multiple links in parallel, and each link
runs many threads.

Remove the limit by specifying --pids-limit -1. Since dbuild is
meant to provide a build environment, not a security barrier,
this is okay (the container is still restricted by host limits).

I checked that --pids-limit is supported by old versions of
docker and by podman.

Fixes #5651.
Message-Id: <20200127090807.3528561-1-avi@scylladb.com>

(cherry picked from commit 897320f6ab)
2020-01-28 18:14:01 +02:00
Piotr Sarna
c0253d9221 db,view: fix checking for secondary index special columns
A mistake in handling legacy checks for special 'idx_token' column
resulted in not recognizing materialized views backing secondary
indexes properly. The mistake is really a typo, but with bad
consequences - instead of checking the view schema for being an index,
we asked for the base schema, which is definitely not an index of
itself.

Branches 3.1,3.2 (asap)
Fixes #5621
Fixes #4744

(cherry picked from commit 9b379e3d63)
2020-01-21 23:32:11 +02:00
2929 changed files with 42405 additions and 106458 deletions

View File

@@ -1,4 +1,3 @@
.git
build
seastar/build
testlog

87
.github/CODEOWNERS vendored
View File

@@ -1,87 +0,0 @@
# AUTH
auth/* @elcallio @vladzcloudius
# CACHE
row_cache* @tgrabiec @haaawk
*mutation* @tgrabiec @haaawk
tests/mvcc* @tgrabiec @haaawk
# CDC
cdc/* @haaawk @kbr- @elcallio @piodul @jul-stas
test/cql/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
test/boost/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
# COMMITLOG / BATCHLOG
db/commitlog/* @elcallio
db/batch* @elcallio
# COORDINATOR
service/storage_proxy* @gleb-cloudius
# COMPACTION
sstables/compaction* @raphaelsc @nyh
# CQL TRANSPORT LAYER
transport/* @penberg
# CQL QUERY LANGUAGE
cql3/* @tgrabiec @penberg @psarna
# COUNTERS
counters* @haaawk @jul-stas
tests/counter_test* @haaawk @jul-stas
# GOSSIP
gms/* @tgrabiec @asias
# DOCKER
dist/docker/* @penberg
# LSA
utils/logalloc* @tgrabiec
# MATERIALIZED VIEWS
db/view/* @nyh @psarna
cql3/statements/*view* @nyh @psarna
test/boost/view_* @nyh @psarna
# PACKAGING
dist/* @syuu1228
# REPAIR
repair/* @tgrabiec @asias @nyh
# SCHEMA MANAGEMENT
db/schema_tables* @tgrabiec @nyh
db/legacy_schema_migrator* @tgrabiec @nyh
service/migration* @tgrabiec @nyh
schema* @tgrabiec @nyh
# SECONDARY INDEXES
db/index/* @nyh @penberg @psarna
cql3/statements/*index* @nyh @penberg @psarna
test/boost/*index* @nyh @penberg @psarna
# SSTABLES
sstables/* @tgrabiec @raphaelsc @nyh
# STREAMING
streaming/* @tgrabiec @asias
service/storage_service.* @tgrabiec @asias
# ALTERNATOR
alternator/* @nyh @psarna
test/alternator/* @nyh @psarna
# HINTED HANDOFF
db/hints/* @haaawk @piodul @vladzcloudius
# REDIS
redis/* @nyh @syuu1228
redis-test/* @nyh @syuu1228
# READERS
reader_* @denesb
querier* @denesb
test/boost/mutation_reader_test.cc @denesb
test/boost/querier_cache_test.cc @denesb

3
.gitignore vendored
View File

@@ -22,6 +22,5 @@ resources
.pytest_cache
/expressions.tokens
tags
testlog
testlog/*
test/*/*.reject
.vscode

20
.gitmodules vendored
View File

@@ -1,23 +1,17 @@
[submodule "seastar"]
path = seastar
url = ../seastar
url = ../scylla-seastar
ignore = dirty
[submodule "swagger-ui"]
path = swagger-ui
url = ../scylla-swagger-ui
ignore = dirty
[submodule "xxHash"]
path = xxHash
url = ../xxHash
[submodule "libdeflate"]
path = libdeflate
url = ../libdeflate
[submodule "abseil"]
path = abseil
url = ../abseil-cpp
[submodule "scylla-jmx"]
path = tools/jmx
url = ../scylla-jmx
[submodule "scylla-tools"]
path = tools/java
url = ../scylla-tools-java
[submodule "scylla-python3"]
path = tools/python3
url = ../scylla-python3
[submodule "zstd"]
path = zstd
url = ../zstd

View File

@@ -1,755 +1,142 @@
cmake_minimum_required(VERSION 3.18)
##
## For best results, first compile the project using the Ninja build-system.
##
cmake_minimum_required(VERSION 3.7)
project(scylla)
if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
message(STATUS "Setting build type to 'Release' as none was specified.")
set(CMAKE_BUILD_TYPE "Release" CACHE
STRING "Choose the type of build." FORCE)
# Set the possible values of build type for cmake-gui
set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
"Debug" "Release" "Dev" "Sanitize")
if (NOT DEFINED FOR_IDE AND NOT DEFINED ENV{FOR_IDE} AND NOT DEFINED ENV{CLION_IDE})
message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in IDEs, please define FOR_IDE to acknowledge this.")
endif()
if(CMAKE_BUILD_TYPE)
string(TOLOWER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
else()
set(BUILD_TYPE "release")
endif()
# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
set(SEASTAR_INCLUDE_DIRS "seastar")
function(default_target_arch arch)
set(x86_instruction_sets i386 i686 x86_64)
if(CMAKE_SYSTEM_PROCESSOR IN_LIST x86_instruction_sets)
set(${arch} "westmere" PARENT_SCOPE)
elseif(CMAKE_SYSTEM_PROCESSOR EQUAL "aarch64")
set(${arch} "armv8-a+crc+crypto" PARENT_SCOPE)
# These paths are always available, since they're included in the repository. Additional DPDK headers are placed while
# Seastar is built, and are captured in `SEASTAR_INCLUDE_DIRS` through parsing the Seastar pkg-config file (below).
set(SEASTAR_DPDK_INCLUDE_DIRS
seastar/dpdk/lib/librte_eal/common/include
seastar/dpdk/lib/librte_eal/common/include/generic
seastar/dpdk/lib/librte_eal/common/include/x86
seastar/dpdk/lib/librte_ether)
find_package(PkgConfig REQUIRED)
set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
pkg_check_modules(SEASTAR seastar)
find_package(Boost COMPONENTS filesystem program_options system thread)
##
## Populate the names of all source and header files in the indicated paths in a designated variable.
##
## When RECURSIVE is specified, directories are traversed recursively.
##
## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
##
function (scan_scylla_source_directories)
set(options RECURSIVE)
set(oneValueArgs VAR)
set(multiValueArgs PATHS)
cmake_parse_arguments(args "${options}" "${oneValueArgs}" "${multiValueArgs}" "${ARGN}")
set(globs "")
foreach (dir ${args_PATHS})
list(APPEND globs "${dir}/*.cc" "${dir}/*.hh")
endforeach()
if (args_RECURSIVE)
set(glob_kind GLOB_RECURSE)
else()
set(${arch} "" PARENT_SCOPE)
set(glob_kind GLOB)
endif()
endfunction()
default_target_arch(target_arch)
if(target_arch)
set(target_arch_flag "-march=${target_arch}")
endif()
# Configure Seastar compile options to align with Scylla
set(Seastar_CXX_FLAGS -fcoroutines ${target_arch_flag} CACHE INTERNAL "" FORCE)
set(Seastar_CXX_DIALECT gnu++20 CACHE INTERNAL "" FORCE)
file(${glob_kind} var
${globs})
add_subdirectory(seastar)
add_subdirectory(abseil)
# Exclude absl::strerror from the default "all" target since it's not
# used in Scylla build and, moreover, makes use of deprecated glibc APIs,
# such as sys_nerr, which are not exposed from "stdio.h" since glibc 2.32,
# which happens to be the case for recent Fedora distribution versions.
#
# Need to use the internal "absl_strerror" target name instead of namespaced
# variant because `set_target_properties` does not understand the latter form,
# unfortunately.
set_target_properties(absl_strerror PROPERTIES EXCLUDE_FROM_ALL TRUE)
# System libraries dependencies
find_package(Boost COMPONENTS filesystem program_options system thread regex REQUIRED)
find_package(Lua REQUIRED)
find_package(ZLIB REQUIRED)
find_package(ICU COMPONENTS uc REQUIRED)
set(scylla_build_dir "${CMAKE_BINARY_DIR}/build/${BUILD_TYPE}")
set(scylla_gen_build_dir "${scylla_build_dir}/gen")
file(MAKE_DIRECTORY "${scylla_build_dir}" "${scylla_gen_build_dir}")
# Place libraries, executables and archives in ${buildroot}/build/${mode}/
foreach(mode RUNTIME LIBRARY ARCHIVE)
set(CMAKE_${mode}_OUTPUT_DIRECTORY "${scylla_build_dir}")
endforeach()
# Generate C++ source files from thrift definitions
function(scylla_generate_thrift)
set(one_value_args TARGET VAR IN_FILE OUT_DIR SERVICE)
cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
get_filename_component(in_file_name ${args_IN_FILE} NAME_WE)
set(aux_out_file_name ${args_OUT_DIR}/${in_file_name})
set(outputs
${aux_out_file_name}_types.cpp
${aux_out_file_name}_types.h
${aux_out_file_name}_constants.cpp
${aux_out_file_name}_constants.h
${args_OUT_DIR}/${args_SERVICE}.cpp
${args_OUT_DIR}/${args_SERVICE}.h)
add_custom_command(
DEPENDS
${args_IN_FILE}
thrift
OUTPUT ${outputs}
COMMAND ${CMAKE_COMMAND} -E make_directory ${args_OUT_DIR}
COMMAND thrift -gen cpp:cob_style,no_skeleton -out "${args_OUT_DIR}" "${args_IN_FILE}")
add_custom_target(${args_TARGET}
DEPENDS ${outputs})
set(${args_VAR} ${outputs} PARENT_SCOPE)
set(${args_VAR} ${var} PARENT_SCOPE)
endfunction()
scylla_generate_thrift(
TARGET scylla_thrift_gen_cassandra
VAR scylla_thrift_gen_cassandra_files
IN_FILE interface/cassandra.thrift
OUT_DIR ${scylla_gen_build_dir}
SERVICE Cassandra)
## Although Seastar is an external project, it is common enough to explore the sources while doing
## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
scan_scylla_source_directories(
VAR SEASTAR_SOURCE_FILES
RECURSIVE
# Parse antlr3 grammar files and generate C++ sources
function(scylla_generate_antlr3)
set(one_value_args TARGET VAR IN_FILE OUT_DIR)
cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
PATHS
seastar/core
seastar/http
seastar/json
seastar/net
seastar/rpc
seastar/tests
seastar/util)
get_filename_component(in_file_pure_name ${args_IN_FILE} NAME)
get_filename_component(stem ${in_file_pure_name} NAME_WE)
scan_scylla_source_directories(
VAR SCYLLA_ROOT_SOURCE_FILES
PATHS .)
set(outputs
"${args_OUT_DIR}/${stem}Lexer.hpp"
"${args_OUT_DIR}/${stem}Lexer.cpp"
"${args_OUT_DIR}/${stem}Parser.hpp"
"${args_OUT_DIR}/${stem}Parser.cpp")
scan_scylla_source_directories(
VAR SCYLLA_SUB_SOURCE_FILES
RECURSIVE
add_custom_command(
DEPENDS
${args_IN_FILE}
OUTPUT ${outputs}
# Remove #ifdef'ed code from the grammar source code
COMMAND sed -e "/^#if 0/,/^#endif/d" "${args_IN_FILE}" > "${args_OUT_DIR}/${in_file_pure_name}"
COMMAND antlr3 "${args_OUT_DIR}/${in_file_pure_name}"
# We replace many local `ExceptionBaseType* ex` variables with a single function-scope one.
# Because we add such a variable to every function, and because `ExceptionBaseType` is not a global
# name, we also add a global typedef to avoid compilation errors.
COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Lexer.hpp"
COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Lexer.cpp"
COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Parser.hpp"
COMMAND sed -i
-e "s/^\\( *\\)\\(ImplTraits::CommonTokenType\\* [a-zA-Z0-9_]* = NULL;\\)$/\\1const \\2/"
-e "/^.*On :.*$/d"
-e "1i using ExceptionBaseType = int;"
-e "s/^{/{ ExceptionBaseType\\* ex = nullptr;/; s/ExceptionBaseType\\* ex = new/ex = new/; s/exceptions::syntax_exception e/exceptions::syntax_exception\\& e/"
"${args_OUT_DIR}/${stem}Parser.cpp"
VERBATIM)
PATHS
api
auth
cql3
db
dht
exceptions
gms
index
io
locator
message
repair
service
sstables
streaming
test
thrift
tracing
transport
utils)
add_custom_target(${args_TARGET}
DEPENDS ${outputs})
scan_scylla_source_directories(
VAR SCYLLA_GEN_SOURCE_FILES
RECURSIVE
PATHS build/release/gen)
set(${args_VAR} ${outputs} PARENT_SCOPE)
endfunction()
set(antlr3_grammar_files
cql3/Cql.g
alternator/expressions.g)
set(antlr3_gen_files)
foreach(f ${antlr3_grammar_files})
get_filename_component(grammar_file_name "${f}" NAME_WE)
get_filename_component(f_dir "${f}" DIRECTORY)
scylla_generate_antlr3(
TARGET scylla_antlr3_gen_${grammar_file_name}
VAR scylla_antlr3_gen_${grammar_file_name}_files
IN_FILE ${f}
OUT_DIR ${scylla_gen_build_dir}/${f_dir})
list(APPEND antlr3_gen_files "${scylla_antlr3_gen_${grammar_file_name}_files}")
endforeach()
# Generate C++ sources from ragel grammar files
seastar_generate_ragel(
TARGET scylla_ragel_gen_protocol_parser
VAR scylla_ragel_gen_protocol_parser_file
IN_FILE redis/protocol_parser.rl
OUT_FILE ${scylla_gen_build_dir}/redis/protocol_parser.hh)
# Generate C++ sources from Swagger definitions
set(swagger_files
api/api-doc/cache_service.json
api/api-doc/collectd.json
api/api-doc/column_family.json
api/api-doc/commitlog.json
api/api-doc/compaction_manager.json
api/api-doc/config.json
api/api-doc/endpoint_snitch_info.json
api/api-doc/error_injection.json
api/api-doc/failure_detector.json
api/api-doc/gossiper.json
api/api-doc/hinted_handoff.json
api/api-doc/lsa.json
api/api-doc/messaging_service.json
api/api-doc/storage_proxy.json
api/api-doc/storage_service.json
api/api-doc/stream_manager.json
api/api-doc/system.json
api/api-doc/utils.json)
set(swagger_gen_files)
foreach(f ${swagger_files})
get_filename_component(fname "${f}" NAME_WE)
get_filename_component(dir "${f}" DIRECTORY)
seastar_generate_swagger(
TARGET scylla_swagger_gen_${fname}
VAR scylla_swagger_gen_${fname}_files
IN_FILE "${f}"
OUT_DIR "${scylla_gen_build_dir}/${dir}")
list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
endforeach()
# Create C++ bindings for IDL serializers
function(scylla_generate_idl_serializer)
set(one_value_args TARGET VAR IN_FILE OUT_FILE)
cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
get_filename_component(out_dir ${args_OUT_FILE} DIRECTORY)
set(idl_compiler "${CMAKE_SOURCE_DIR}/idl-compiler.py")
find_package(Python3 COMPONENTS Interpreter)
add_custom_command(
DEPENDS
${args_IN_FILE}
${idl_compiler}
OUTPUT ${args_OUT_FILE}
COMMAND ${CMAKE_COMMAND} -E make_directory ${out_dir}
COMMAND Python3::Interpreter ${idl_compiler} --ns ser -f ${args_IN_FILE} -o ${args_OUT_FILE})
add_custom_target(${args_TARGET}
DEPENDS ${args_OUT_FILE})
set(${args_VAR} ${args_OUT_FILE} PARENT_SCOPE)
endfunction()
set(idl_serializers
idl/cache_temperature.idl.hh
idl/commitlog.idl.hh
idl/consistency_level.idl.hh
idl/frozen_mutation.idl.hh
idl/frozen_schema.idl.hh
idl/gossip_digest.idl.hh
idl/idl_test.idl.hh
idl/keys.idl.hh
idl/messaging_service.idl.hh
idl/mutation.idl.hh
idl/paging_state.idl.hh
idl/partition_checksum.idl.hh
idl/paxos.idl.hh
idl/query.idl.hh
idl/range.idl.hh
idl/read_command.idl.hh
idl/reconcilable_result.idl.hh
idl/replay_position.idl.hh
idl/result.idl.hh
idl/ring_position.idl.hh
idl/streaming.idl.hh
idl/token.idl.hh
idl/tracing.idl.hh
idl/truncation_record.idl.hh
idl/uuid.idl.hh
idl/view.idl.hh)
set(idl_gen_files)
foreach(f ${idl_serializers})
get_filename_component(idl_name "${f}" NAME)
get_filename_component(idl_target "${idl_name}" NAME_WE)
get_filename_component(idl_dir "${f}" DIRECTORY)
string(REPLACE ".idl.hh" ".dist.hh" idl_out_hdr_name "${idl_name}")
scylla_generate_idl_serializer(
TARGET scylla_idl_gen_${idl_target}
VAR scylla_idl_gen_${idl_target}_files
IN_FILE ${f}
OUT_FILE ${scylla_gen_build_dir}/${idl_dir}/${idl_out_hdr_name})
list(APPEND idl_gen_files "${scylla_idl_gen_${idl_target}_files}")
endforeach()
set(scylla_sources
absl-flat_hash_map.cc
alternator/auth.cc
alternator/base64.cc
alternator/conditions.cc
alternator/executor.cc
alternator/expressions.cc
alternator/serialization.cc
alternator/server.cc
alternator/stats.cc
alternator/streams.cc
api/api.cc
api/cache_service.cc
api/collectd.cc
api/column_family.cc
api/commitlog.cc
api/compaction_manager.cc
api/config.cc
api/endpoint_snitch.cc
api/error_injection.cc
api/failure_detector.cc
api/gossiper.cc
api/hinted_handoff.cc
api/lsa.cc
api/messaging_service.cc
api/storage_proxy.cc
api/storage_service.cc
api/stream_manager.cc
api/system.cc
atomic_cell.cc
auth/allow_all_authenticator.cc
auth/allow_all_authorizer.cc
auth/authenticated_user.cc
auth/authentication_options.cc
auth/authenticator.cc
auth/common.cc
auth/default_authorizer.cc
auth/password_authenticator.cc
auth/passwords.cc
auth/permission.cc
auth/permissions_cache.cc
auth/resource.cc
auth/role_or_anonymous.cc
auth/roles-metadata.cc
auth/sasl_challenge.cc
auth/service.cc
auth/standard_role_manager.cc
auth/transitional.cc
bytes.cc
canonical_mutation.cc
cdc/cdc_partitioner.cc
cdc/generation.cc
cdc/log.cc
cdc/metadata.cc
cdc/split.cc
clocks-impl.cc
collection_mutation.cc
compress.cc
connection_notifier.cc
converting_mutation_partition_applier.cc
counters.cc
cql3/abstract_marker.cc
cql3/attributes.cc
cql3/cf_name.cc
cql3/column_condition.cc
cql3/column_identifier.cc
cql3/column_specification.cc
cql3/constants.cc
cql3/cql3_type.cc
cql3/expr/expression.cc
cql3/functions/aggregate_fcts.cc
cql3/functions/castas_fcts.cc
cql3/functions/error_injection_fcts.cc
cql3/functions/functions.cc
cql3/functions/user_function.cc
cql3/index_name.cc
cql3/keyspace_element_name.cc
cql3/lists.cc
cql3/maps.cc
cql3/operation.cc
cql3/query_options.cc
cql3/query_processor.cc
cql3/relation.cc
cql3/restrictions/statement_restrictions.cc
cql3/result_set.cc
cql3/role_name.cc
cql3/selection/abstract_function_selector.cc
cql3/selection/selectable.cc
cql3/selection/selection.cc
cql3/selection/selector.cc
cql3/selection/selector_factories.cc
cql3/selection/simple_selector.cc
cql3/sets.cc
cql3/single_column_relation.cc
cql3/statements/alter_keyspace_statement.cc
cql3/statements/alter_table_statement.cc
cql3/statements/alter_type_statement.cc
cql3/statements/alter_view_statement.cc
cql3/statements/authentication_statement.cc
cql3/statements/authorization_statement.cc
cql3/statements/batch_statement.cc
cql3/statements/cas_request.cc
cql3/statements/cf_prop_defs.cc
cql3/statements/cf_statement.cc
cql3/statements/create_function_statement.cc
cql3/statements/create_index_statement.cc
cql3/statements/create_keyspace_statement.cc
cql3/statements/create_table_statement.cc
cql3/statements/create_type_statement.cc
cql3/statements/create_view_statement.cc
cql3/statements/delete_statement.cc
cql3/statements/drop_function_statement.cc
cql3/statements/drop_index_statement.cc
cql3/statements/drop_keyspace_statement.cc
cql3/statements/drop_table_statement.cc
cql3/statements/drop_type_statement.cc
cql3/statements/drop_view_statement.cc
cql3/statements/function_statement.cc
cql3/statements/grant_statement.cc
cql3/statements/index_prop_defs.cc
cql3/statements/index_target.cc
cql3/statements/ks_prop_defs.cc
cql3/statements/list_permissions_statement.cc
cql3/statements/list_users_statement.cc
cql3/statements/modification_statement.cc
cql3/statements/permission_altering_statement.cc
cql3/statements/property_definitions.cc
cql3/statements/raw/parsed_statement.cc
cql3/statements/revoke_statement.cc
cql3/statements/role-management-statements.cc
cql3/statements/schema_altering_statement.cc
cql3/statements/select_statement.cc
cql3/statements/truncate_statement.cc
cql3/statements/update_statement.cc
cql3/statements/use_statement.cc
cql3/token_relation.cc
cql3/tuples.cc
cql3/type_json.cc
cql3/untyped_result_set.cc
cql3/update_parameters.cc
cql3/user_types.cc
cql3/ut_name.cc
cql3/util.cc
cql3/values.cc
cql3/variable_specifications.cc
data/cell.cc
database.cc
db/batchlog_manager.cc
db/commitlog/commitlog.cc
db/commitlog/commitlog_entry.cc
db/commitlog/commitlog_replayer.cc
db/config.cc
db/consistency_level.cc
db/cql_type_parser.cc
db/data_listeners.cc
db/extensions.cc
db/heat_load_balance.cc
db/hints/manager.cc
db/hints/resource_manager.cc
db/large_data_handler.cc
db/legacy_schema_migrator.cc
db/marshal/type_parser.cc
db/schema_tables.cc
db/size_estimates_virtual_reader.cc
db/snapshot-ctl.cc
db/sstables-format-selector.cc
db/system_distributed_keyspace.cc
db/system_keyspace.cc
db/view/row_locking.cc
db/view/view.cc
db/view/view_update_generator.cc
dht/boot_strapper.cc
dht/i_partitioner.cc
dht/murmur3_partitioner.cc
dht/range_streamer.cc
dht/token.cc
distributed_loader.cc
duration.cc
exceptions/exceptions.cc
flat_mutation_reader.cc
frozen_mutation.cc
frozen_schema.cc
gms/application_state.cc
gms/endpoint_state.cc
gms/failure_detector.cc
gms/feature_service.cc
gms/gossip_digest_ack.cc
gms/gossip_digest_ack2.cc
gms/gossip_digest_syn.cc
gms/gossiper.cc
gms/inet_address.cc
gms/version_generator.cc
gms/versioned_value.cc
hashers.cc
index/secondary_index.cc
index/secondary_index_manager.cc
init.cc
keys.cc
lister.cc
locator/abstract_replication_strategy.cc
locator/ec2_multi_region_snitch.cc
locator/ec2_snitch.cc
locator/everywhere_replication_strategy.cc
locator/gce_snitch.cc
locator/gossiping_property_file_snitch.cc
locator/local_strategy.cc
locator/network_topology_strategy.cc
locator/production_snitch_base.cc
locator/rack_inferring_snitch.cc
locator/simple_snitch.cc
locator/simple_strategy.cc
locator/snitch_base.cc
locator/token_metadata.cc
lua.cc
main.cc
memtable.cc
message/messaging_service.cc
multishard_mutation_query.cc
mutation.cc
raft/fsm.cc
raft/log.cc
raft/progress.cc
raft/raft.cc
raft/server.cc
mutation_fragment.cc
mutation_partition.cc
mutation_partition_serializer.cc
mutation_partition_view.cc
mutation_query.cc
mutation_reader.cc
mutation_writer/multishard_writer.cc
mutation_writer/shard_based_splitting_writer.cc
mutation_writer/timestamp_based_splitting_writer.cc
partition_slice_builder.cc
partition_version.cc
querier.cc
query-result-set.cc
query.cc
range_tombstone.cc
range_tombstone_list.cc
reader_concurrency_semaphore.cc
redis/abstract_command.cc
redis/command_factory.cc
redis/commands.cc
redis/keyspace_utils.cc
redis/lolwut.cc
redis/mutation_utils.cc
redis/options.cc
redis/query_processor.cc
redis/query_utils.cc
redis/server.cc
redis/service.cc
redis/stats.cc
repair/repair.cc
repair/row_level.cc
row_cache.cc
schema.cc
schema_mutations.cc
schema_registry.cc
service/client_state.cc
service/migration_manager.cc
service/migration_task.cc
service/misc_services.cc
service/pager/paging_state.cc
service/pager/query_pagers.cc
service/paxos/paxos_state.cc
service/paxos/prepare_response.cc
service/paxos/prepare_summary.cc
service/paxos/proposal.cc
service/priority_manager.cc
service/storage_proxy.cc
service/storage_service.cc
sstables/compaction.cc
sstables/compaction_manager.cc
sstables/compaction_strategy.cc
sstables/compress.cc
sstables/integrity_checked_file_impl.cc
sstables/kl/writer.cc
sstables/leveled_compaction_strategy.cc
sstables/m_format_read_helpers.cc
sstables/metadata_collector.cc
sstables/mp_row_consumer.cc
sstables/mx/writer.cc
sstables/partition.cc
sstables/prepended_input_stream.cc
sstables/random_access_reader.cc
sstables/size_tiered_compaction_strategy.cc
sstables/sstable_directory.cc
sstables/sstable_version.cc
sstables/sstables.cc
sstables/sstables_manager.cc
sstables/time_window_compaction_strategy.cc
sstables/writer.cc
streaming/progress_info.cc
streaming/session_info.cc
streaming/stream_coordinator.cc
streaming/stream_manager.cc
streaming/stream_plan.cc
streaming/stream_reason.cc
streaming/stream_receive_task.cc
streaming/stream_request.cc
streaming/stream_result_future.cc
streaming/stream_session.cc
streaming/stream_session_state.cc
streaming/stream_summary.cc
streaming/stream_task.cc
streaming/stream_transfer_task.cc
table.cc
table_helper.cc
thrift/controller.cc
thrift/handler.cc
thrift/server.cc
thrift/thrift_validation.cc
timeout_config.cc
tracing/trace_keyspace_helper.cc
tracing/trace_state.cc
tracing/traced_file.cc
tracing/tracing.cc
tracing/tracing_backend_registry.cc
transport/controller.cc
transport/cql_protocol_extension.cc
transport/event.cc
transport/event_notifier.cc
transport/messages/result_message.cc
transport/server.cc
types.cc
unimplemented.cc
utils/UUID_gen.cc
utils/arch/powerpc/crc32-vpmsum/crc32_wrapper.cc
utils/array-search.cc
utils/ascii.cc
utils/big_decimal.cc
utils/bloom_calculations.cc
utils/bloom_filter.cc
utils/buffer_input_stream.cc
utils/build_id.cc
utils/config_file.cc
utils/directories.cc
utils/disk-error-handler.cc
utils/dynamic_bitset.cc
utils/error_injection.cc
utils/exceptions.cc
utils/file_lock.cc
utils/generation-number.cc
utils/gz/crc_combine.cc
utils/human_readable.cc
utils/i_filter.cc
utils/large_bitset.cc
utils/like_matcher.cc
utils/limiting_data_source.cc
utils/logalloc.cc
utils/managed_bytes.cc
utils/multiprecision_int.cc
utils/murmur_hash.cc
utils/rate_limiter.cc
utils/rjson.cc
utils/runtime.cc
utils/updateable_value.cc
utils/utf8.cc
utils/uuid.cc
validation.cc
vint-serialization.cc
zstd.cc
release.cc)
set(scylla_gen_sources
"${scylla_thrift_gen_cassandra_files}"
"${scylla_ragel_gen_protocol_parser_file}"
"${swagger_gen_files}"
"${idl_gen_files}"
"${antlr3_gen_files}")
set(SCYLLA_SOURCE_FILES
${SCYLLA_ROOT_SOURCE_FILES}
${SCYLLA_GEN_SOURCE_FILES}
${SCYLLA_SUB_SOURCE_FILES})
add_executable(scylla
${scylla_sources}
${scylla_gen_sources})
${SEASTAR_SOURCE_FILES}
${SCYLLA_SOURCE_FILES})
target_link_libraries(scylla PRIVATE
seastar
# Boost dependencies
Boost::filesystem
Boost::program_options
Boost::system
Boost::thread
Boost::regex
Boost::headers
# Abseil libs
absl::hashtablez_sampler
absl::raw_hash_set
absl::synchronization
absl::graphcycles_internal
absl::stacktrace
absl::symbolize
absl::debugging_internal
absl::demangle_internal
absl::time
absl::time_zone
absl::int128
absl::city
absl::hash
absl::malloc_internal
absl::spinlock_wait
absl::base
absl::dynamic_annotations
absl::raw_logging_internal
absl::exponential_biased
absl::throw_delegate
# System libs
ZLIB::ZLIB
ICU::uc
systemd
zstd
snappy
${LUA_LIBRARIES}
thrift
crypt)
# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
target_link_libraries(scylla PRIVATE
-Wl,--build-id=sha1 # Force SHA1 build-id generation
# TODO: Use lld linker if it's available, otherwise gold, else bfd
-fuse-ld=lld)
# TODO: patch dynamic linker to match configure.py behavior
# If the Seastar pkg-config information is available, append to the default flags.
#
# For ease of browsing the source code, we always pretend that DPDK is enabled.
target_compile_options(scylla PUBLIC
-std=gnu++1z
-DHAVE_DPDK
-DHAVE_HWLOC
"${SEASTAR_CFLAGS}")
target_compile_options(scylla PRIVATE
-std=gnu++20
-fcoroutines # TODO: Clang does not have this flag, adjust to both variants
${target_arch_flag})
# Hacks needed to expose internal APIs for xxhash dependencies
target_compile_definitions(scylla PRIVATE XXH_PRIVATE_API HAVE_LZ4_COMPRESS_DEFAULT)
target_include_directories(scylla PRIVATE
"${CMAKE_CURRENT_SOURCE_DIR}"
libdeflate
abseil
"${scylla_gen_build_dir}")
###
### Create crc_combine_table helper executable.
### Use it to generate crc_combine_table.cc to be used in scylla at build time.
###
add_executable(crc_combine_table utils/gz/gen_crc_combine_table.cc)
target_link_libraries(crc_combine_table PRIVATE seastar)
target_include_directories(crc_combine_table PRIVATE "${CMAKE_CURRENT_SOURCE_DIR}")
target_compile_options(crc_combine_table PRIVATE
-std=gnu++20
-fcoroutines
${target_arch_flag})
add_dependencies(scylla crc_combine_table)
# Generate an additional source file at build time that is needed for Scylla compilation
add_custom_command(OUTPUT "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc"
COMMAND $<TARGET_FILE:crc_combine_table> > "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc"
DEPENDS crc_combine_table)
target_sources(scylla PRIVATE "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc")
###
### Generate version file and supply appropriate compile definitions for release.cc
###
execute_process(COMMAND ${CMAKE_SOURCE_DIR}/SCYLLA-VERSION-GEN RESULT_VARIABLE scylla_version_gen_res)
if(scylla_version_gen_res)
message(SEND_ERROR "Version file generation failed. Return code: ${scylla_version_gen_res}")
endif()
file(READ build/SCYLLA-VERSION-FILE scylla_version)
string(STRIP "${scylla_version}" scylla_version)
file(READ build/SCYLLA-RELEASE-FILE scylla_release)
string(STRIP "${scylla_release}" scylla_release)
get_property(release_cdefs SOURCE "${CMAKE_SOURCE_DIR}/release.cc" PROPERTY COMPILE_DEFINITIONS)
list(APPEND release_cdefs "SCYLLA_VERSION=\"${scylla_version}\"" "SCYLLA_RELEASE=\"${scylla_release}\"")
set_source_files_properties("${CMAKE_SOURCE_DIR}/release.cc" PROPERTIES COMPILE_DEFINITIONS "${release_cdefs}")
###
### Custom command for building libdeflate. Link the library to scylla.
###
set(libdeflate_lib "${scylla_build_dir}/libdeflate/libdeflate.a")
add_custom_command(OUTPUT "${libdeflate_lib}"
COMMAND make -C libdeflate
BUILD_DIR=../build/${BUILD_TYPE}/libdeflate/
CC=${CMAKE_C_COMPILER}
"CFLAGS=${target_arch_flag}"
../build/${BUILD_TYPE}/libdeflate//libdeflate.a) # Two backslashes are important!
# Hack to force generating custom command to produce libdeflate.a
add_custom_target(libdeflate DEPENDS "${libdeflate_lib}")
target_link_libraries(scylla PRIVATE "${libdeflate_lib}")
# TODO: create cmake/ directory and move utilities (generate functions etc) there
# TODO: Build tests if BUILD_TESTING=on (using CTest module)
# The order matters here: prefer the "static" DPDK directories to any dynamic paths from pkg-config. Some files are only
# available dynamically, though.
target_include_directories(scylla PUBLIC
.
${SEASTAR_DPDK_INCLUDE_DIRS}
${SEASTAR_INCLUDE_DIRS}
${Boost_INCLUDE_DIRS}
xxhash
libdeflate
build/release/gen)

View File

@@ -8,4 +8,4 @@ Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to re
# Contributing Code to Scylla
To contribute code to Scylla, you need to sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.
To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

View File

@@ -18,35 +18,23 @@ $ git submodule update --init --recursive
### Dependencies
Scylla is fairly fussy about its build environment, requiring a very recent
version of the C++20 compiler and numerous tools and libraries to build.
Scylla depends on the system package manager for its development dependencies.
Run `./install-dependencies.sh` (as root) to use your Linux distributions's
package manager to install the appropriate packages on your build machine.
However, this will only work on very recent distributions. For example,
currently Fedora users must upgrade to Fedora 32 otherwise the C++ compiler
will be too old, and not support the new C++20 standard that Scylla uses.
Running `./install-dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
Alternatively, to avoid having to upgrade your build machine or install
various packages on it, we provide another option - the **frozen toolchain**.
This is a script, `./tools/toolchain/dbuild`, that can execute build or run
commands inside a Docker image that contains exactly the right build tools and
libraries. The `dbuild` technique is useful for beginners, but is also the way
in which ScyllaDB produces official releases, so it is highly recommended.
On Ubuntu and Debian based Linux distributions, some packages
required to build Scylla are missing in the official upstream:
To use `dbuild`, you simply prefix any build or run command with it. Building
and running Scylla becomes as easy as:
- libthrift-dev and libthrift
- antlr3-c++-dev
```bash
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla
$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
```
Try running ```sudo ./scripts/scylla_current_repo``` to add Scylla upstream,
and get the missing packages from it.
### Build system
**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
thread, and up to 3 GB per native thread while linking. GCC >= 10 is
thread, and up to 3 GB per native thread while linking. GCC >= 8.1.1. is
required.
Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
@@ -153,7 +141,7 @@ In v3:
"Tests: unit ({mode}), dtest ({smp})"
```
The usual is "Tests: unit (dev)", although running debug tests is encouraged.
The usual is "Tests: unit (release)", although running debug tests is encouraged.
5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.

114
MAINTAINERS Normal file
View File

@@ -0,0 +1,114 @@
M: Maintainer with commit access
R: Reviewer with subsystem expertise
F: Filename, directory, or pattern for the subsystem
---
AUTH
R: Calle Wilund <calle@scylladb.com>
R: Vlad Zolotarov <vladz@scylladb.com>
R: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
F: auth/*
CACHE
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Piotr Jastrzebski <piotr@scylladb.com>
F: row_cache*
F: *mutation*
F: tests/mvcc*
COMMITLOG / BATCHLOGa
R: Calle Wilund <calle@scylladb.com>
F: db/commitlog/*
F: db/batch*
COORDINATOR
R: Gleb Natapov <gleb@scylladb.com>
F: service/storage_proxy*
COMPACTION
R: Raphael S. Carvalho <raphaelsc@scylladb.com>
R: Glauber Costa <glauber@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: sstables/compaction*
CQL TRANSPORT LAYER
M: Pekka Enberg <penberg@scylladb.com>
F: transport/*
CQL QUERY LANGUAGE
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Pekka Enberg <penberg@scylladb.com>
F: cql3/*
COUNTERS
F: counters*
F: tests/counter_test*
GOSSIP
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
F: gms/*
DOCKER
M: Pekka Enberg <penberg@scylladb.com>
F: dist/docker/*
LSA
M: Tomasz Grabiec <tgrabiec@scylladb.com>
F: utils/logalloc*
MATERIALIZED VIEWS
M: Pekka Enberg <penberg@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
F: db/view/*
F: cql3/statements/*view*
PACKAGING
R: Takuya ASADA <syuu@scylladb.com>
F: dist/*
REPAIR
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: repair/*
SCHEMA MANAGEMENT
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Pekka Enberg <penberg@scylladb.com>
F: db/schema_tables*
F: db/legacy_schema_migrator*
F: service/migration*
F: schema*
SECONDARY INDEXES
M: Pekka Enberg <penberg@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
R: Pekka Enberg <penberg@scylladb.com>
F: db/index/*
F: cql3/statements/*index*
SSTABLES
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Raphael S. Carvalho <raphaelsc@scylladb.com>
R: Glauber Costa <glauber@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: sstables/*
STREAMING
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
F: streaming/*
F: service/storage_service.*
ALTERNATOR
M: Nadav Har'El <nyh@scylladb.com>
F: alternator/*
F: alternator-test/*
THE REST
M: Avi Kivity <avi@scylladb.com>
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
F: *

View File

@@ -1,7 +1,5 @@
This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
especially Apache Cassandra.
It includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
It also includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.
It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)

146
README.md
View File

@@ -1,78 +1,49 @@
# Scylla
[![Slack](https://img.shields.io/badge/slack-scylla-brightgreen.svg?logo=slack)](http://slack.scylladb.com)
[![Twitter](https://img.shields.io/twitter/follow/ScyllaDB.svg?style=social&label=Follow)](https://twitter.com/intent/follow?screen_name=ScyllaDB)
## Quick-start
## What is Scylla?
Scylla is the real-time big data database that is API-compatible with Apache Cassandra and Amazon DynamoDB.
Scylla embraces a shared-nothing approach that increases throughput and storage capacity to realize order-of-magnitude performance improvements and reduce hardware costs.
For more information, please see the [ScyllaDB web site].
[ScyllaDB web site]: https://www.scylladb.com
## Build Prerequisites
Scylla is fairly fussy about its build environment, requiring very recent
versions of the C++20 compiler and of many libraries to build. The document
[HACKING.md](HACKING.md) includes detailed information on building and
developing Scylla, but to get Scylla building quickly on (almost) any build
machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md),
This is a pre-configured Docker image which includes recent versions of all
the required compilers, libraries and build tools. Using the frozen toolchain
allows you to avoid changing anything in your build machine to meet Scylla's
requirements - you just need to meet the frozen toolchain's prerequisites
(mostly, Docker or Podman being available).
## Building Scylla
Building Scylla with the frozen toolchain `dbuild` is as easy as:
To get the build going quickly, Scylla offers a [frozen toolchain](tools/toolchain/README.md)
which would build and run Scylla using a pre-configured Docker image.
Using the frozen toolchain will also isolate all of the installed
dependencies in a Docker container.
Assuming you have met the toolchain prerequisites, which is running
Docker in user mode, building and running is as easy as:
```bash
$ git submodule update --init --force --recursive
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla
```
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla
$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
```
For further information, please see:
Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
* [Developer documentation] for more information on building Scylla.
* [Build documentation] on how to build Scylla binaries, tests, and packages.
* [Docker image build documentation] for information on how to build Docker images.
[developer documentation]: HACKING.md
[build documentation]: docs/building.md
[docker image build documentation]: dist/docker/redhat/README.md
**Note**: GCC >= 8.1.1 is required to compile Scylla.
## Running Scylla
To start Scylla server, run:
* Run Scylla
```
./build/release/scylla
```bash
$ ./tools/toolchain/dbuild ./build/release/scylla --workdir tmp --smp 1 --developer-mode 1
```
This will start a Scylla node with one CPU core allocated to it and data files stored in the `tmp` directory.
The `--developer-mode` is needed to disable the various checks Scylla performs at startup to ensure the machine is configured for maximum performance (not relevant on development workstations).
Please note that you need to run Scylla with `dbuild` if you built it with the frozen toolchain.
* run Scylla with one CPU and ./tmp as work directory
For more run options, run:
```bash
$ ./tools/toolchain/dbuild ./build/release/scylla --help
```
./build/release/scylla --workdir tmp --smp 1
```
## Testing
See [test.py manual](docs/testing.md).
* For more run options:
```
./build/release/scylla --help
```
## Scylla APIs and compatibility
By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
Thrift. There is also support for the API of Amazon DynamoDB,
which needs to be enabled and configured in order to be used. For more
information on how to enable the DynamoDB™ API in Scylla,
and the current compatibility of this feature as well as Scylla-specific extensions, see
Thrift. There is also experimental support for the API of Amazon DynamoDB,
but being experimental it needs to be explicitly enabled to be used. For more
information on how to enable the experimental DynamoDB compatibility in Scylla,
and the current limitations of this feature, see
[Alternator](docs/alternator/alternator.md) and
[Getting started with Alternator](docs/alternator/getting-started.md).
@@ -85,29 +56,48 @@ both.
Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
User documentation can be found [here](https://docs.scylladb.com/).
## Training
## Building Fedora RPM
Training material and online courses can be found at [Scylla University](https://university.scylladb.com/).
The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling,
administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions,
multi-datacenters and how Scylla integrates with third-party applications.
As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
```
# Install mock:
sudo yum install mock
# Add user to the "mock" group:
usermod -a -G mock $USER && newgrp mock
```
Then, to build an RPM, run:
```
./dist/redhat/build_rpm.sh
```
The built RPM is stored in ``/var/lib/mock/<configuration>/result`` directory.
For example, on Fedora 21 mock reports the following:
```
INFO: Done(scylla-server-0.00-1.fc21.src.rpm) Config(default) 20 minutes 7 seconds
INFO: Results and/or logs in: /var/lib/mock/fedora-21-x86_64/result
```
## Building Fedora-based Docker image
Build a Docker image with:
```
cd dist/docker
docker build -t <image-name> .
```
Run the image with:
```
docker run -p $(hostname -i):9042:9042 -i -t <image name>
```
## Contributing to Scylla
If you want to report a bug or submit a pull request or a patch, please read the [contribution guidelines].
If you are a developer working on Scylla, please read the [developer guidelines].
[contribution guidelines]: CONTRIBUTING.md
[developer guidelines]: HACKING.md
## Contact
* The [users mailing list] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
* The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
[Users mailing list]: https://groups.google.com/forum/#!forum/scylladb-users
[Slack channel]: http://slack.scylladb.com/
[Developers mailing list]: https://groups.google.com/forum/#!forum/scylladb-dev
[Hacking howto](HACKING.md)
[Guidelines for contributing](CONTRIBUTING.md)

View File

@@ -1,7 +1,7 @@
#!/bin/sh
PRODUCT=scylla
VERSION=4.4.dev
VERSION=3.3.4
if test -f version
then
@@ -19,14 +19,6 @@ else
SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
fi
if [ -f build/SCYLLA-RELEASE-FILE ]; then
RELEASE_FILE=$(cat build/SCYLLA-RELEASE-FILE)
GIT_COMMIT_FILE=$(cat build/SCYLLA-RELEASE-FILE |cut -d . -f 3)
if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
exit 0
fi
fi
echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
mkdir -p build
echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE

1
abseil

Submodule abseil deleted from 1e3d25b265

View File

@@ -1,26 +0,0 @@
/*
* Copyright (C) 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "absl-flat_hash_map.hh"
size_t sstring_hash::operator()(std::string_view v) const noexcept {
return absl::Hash<std::string_view>{}(v);
}

View File

@@ -1,47 +0,0 @@
/*
* Copyright (C) 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <absl/container/flat_hash_map.h>
#include <seastar/core/sstring.hh>
using namespace seastar;
struct sstring_hash {
using is_transparent = void;
size_t operator()(std::string_view v) const noexcept;
};
struct sstring_eq {
using is_transparent = void;
bool operator()(std::string_view a, std::string_view b) const noexcept {
return a == b;
}
};
template <typename K, typename V, typename... Ts>
struct flat_hash_map : public absl::flat_hash_map<K, V, Ts...> {
};
template <typename V>
struct flat_hash_map<sstring, V>
: public absl::flat_hash_map<sstring, V, sstring_hash, sstring_eq> {};

View File

@@ -26,14 +26,6 @@ import pytest
import boto3
from util import create_test_table
# When tests are run with HTTPS, the server often won't have its SSL
# certificate signed by a known authority. So we will disable certificate
# verification with the "verify=False" request option. However, once we do
# that, we start getting scary-looking warning messages, saying that this
# makes HTTPS insecure. The following silences those warnings:
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
# Test that the Boto libraries are new enough. These tests want to test a
# large variety of DynamoDB API features, and to do this we need a new-enough
# version of the the Boto libraries (boto3 and botocore) so that they can
@@ -54,8 +46,6 @@ def pytest_addoption(parser):
parser.addoption("--https", action="store_true",
help="communicate via HTTPS protocol on port 8043 instead of HTTP when"
" running against a local Scylla installation")
parser.addoption("--url", action="store",
help="communicate with given URL instead of defaults")
# "dynamodb" fixture: set up client object for communicating with the DynamoDB
# API. Currently this chooses either Amazon's DynamoDB in the default region
@@ -72,34 +62,15 @@ def dynamodb(request):
# requires us to specify dummy region and credential parameters,
# otherwise the user is forced to properly configure ~/.aws even
# for local runs.
if request.config.getoption('url') != None:
local_url = request.config.getoption('url')
else:
local_url = 'https://localhost:8043' if request.config.getoption('https') else 'http://localhost:8000'
local_url = 'https://localhost:8043' if request.config.getoption('https') else 'http://localhost:8000'
# Disable verifying in order to be able to use self-signed TLS certificates
verify = not request.config.getoption('https')
# Silencing the 'Unverified HTTPS request warning'
if request.config.getoption('https'):
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
return boto3.resource('dynamodb', endpoint_url=local_url, verify=verify,
region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass',
config=botocore.client.Config(retries={"max_attempts": 3}))
@pytest.fixture(scope="session")
def dynamodbstreams(request):
if request.config.getoption('aws'):
return boto3.client('dynamodbstreams')
else:
# Even though we connect to the local installation, Boto3 still
# requires us to specify dummy region and credential parameters,
# otherwise the user is forced to properly configure ~/.aws even
# for local runs.
if request.config.getoption('url') != None:
local_url = request.config.getoption('url')
else:
local_url = 'https://localhost:8043' if request.config.getoption('https') else 'http://localhost:8000'
# Disable verifying in order to be able to use self-signed TLS certificates
verify = not request.config.getoption('https')
return boto3.client('dynamodbstreams', endpoint_url=local_url, verify=verify,
region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass',
config=botocore.client.Config(retries={"max_attempts": 3}))
region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass')
# "test_table" fixture: Create and return a temporary table to be used in tests
# that need a table to work on. The table is automatically deleted at the end.
@@ -144,15 +115,6 @@ def test_table_s(dynamodb):
AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
yield table
table.delete()
# test_table_s_2 has exactly the same schema as test_table_s, and is useful
# for tests which need two different tables with the same schema.
@pytest.fixture(scope="session")
def test_table_s_2(dynamodb):
table = create_test_table(dynamodb,
KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, ],
AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
yield table
table.delete()
@pytest.fixture(scope="session")
def test_table_b(dynamodb):
table = create_test_table(dynamodb,
@@ -174,13 +136,6 @@ def test_table_sn(dynamodb):
AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'N' } ])
yield table
table.delete()
@pytest.fixture(scope="session")
def test_table_ss(dynamodb):
table = create_test_table(dynamodb,
KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'S' } ])
yield table
table.delete()
# "filled_test_table" fixture: Create a temporary table to be used in tests
# that involve reading data - GetItem, Scan, etc. The table is filled with
@@ -222,11 +177,3 @@ def filled_test_table(dynamodb):
yield table, items
table.delete()
# The "scylla_only" fixture can be used by tests for Scylla-only features,
# which do not exist on AWS DynamoDB. A test using this fixture will be
# skipped if running with "--aws".
@pytest.fixture(scope="session")
def scylla_only(dynamodb):
if dynamodb.meta.client._endpoint.host.endswith('.amazonaws.com'):
pytest.skip('Scylla-only feature not supported by AWS')

View File

@@ -59,18 +59,6 @@ def test_expired_signature(dynamodb, test_table):
assert not response.ok
assert "InvalidSignatureException" in response.text and "Signature expired" in response.text
# A test verifying that missing Authorization header is handled properly
def test_no_authorization_header(dynamodb, test_table):
url = dynamodb.meta.client._endpoint.host
print(url)
headers = {'Content-Type': 'application/x-amz-json-1.0',
'X-Amz-Date': '20170101T010101Z',
'X-Amz-Target': 'DynamoDB_20120810.DescribeEndpoints',
}
response = requests.post(url, headers=headers, verify=False)
assert not response.ok
assert "InvalidSignatureException" in response.text and "Authorization header" in response.text
# A test ensuring that signatures that exceed current time too much are not accepted.
# Watch out - this test is valid only for around next 1000 years, it needs to be updated later.
def test_signature_too_futuristic(dynamodb, test_table):

View File

@@ -20,7 +20,6 @@
# so they are actually tested by other tests as well.
import pytest
import random
from botocore.exceptions import ClientError
from util import random_string, full_scan, full_query, multiset
@@ -45,19 +44,6 @@ def test_basic_batch_write_item(test_table):
assert item['attribute'] == str(i)
assert item['another'] == 'xyz'
# Try a batch which includes both multiple writes to the same partition
# and several partitions. The LWT code collects multiple mutations to the
# same partition together, and we want to test that this worked correctly.
def test_batch_write_item_mixed(test_table):
partitions = [random_string() for i in range(4)]
items = [{'p': p, 'c': str(i)} for p in partitions for i in range(4)]
with test_table.batch_writer() as batch:
# Reorder items randomly, just for the heck of it
for item in random.sample(items, len(items)):
batch.put_item(item)
for item in items:
assert test_table.get_item(Key={'p': item['p'], 'c': item['c']}, ConsistentRead=True)['Item'] == item
# Test batch write to a table with only a hash key
def test_batch_write_hash_only(test_table_s):
items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
@@ -152,20 +138,6 @@ def test_batch_write_duplicate_write_and_delete(test_table_s, test_table):
batch.put_item({'p': p, 'c': other})
batch.put_item({'p': other, 'c': c})
# The BatchWriteIem API allows writing to more than one table in the same
# batch. This test verifies that the duplicate-key checking doesn't mistake
# updates to the same key in different tables to be duplicates.
def test_batch_write_nonduplicate_multiple_tables(test_table_s, test_table_s_2):
p = random_string()
# The batch_writer() function used in previous tests can't write to more
# than one table. So we use the lower level interface boto3 gives us.
reply = test_table_s.meta.client.batch_write_item(RequestItems = {
test_table_s.name: [{'PutRequest': {'Item': {'p': p, 'a': 'hi'}}}],
test_table_s_2.name: [{'PutRequest': {'Item': {'p': p, 'b': 'hello'}}}]
})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi'}
assert test_table_s_2.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
# Test that BatchWriteItem's PutRequest completely replaces an existing item.
# It shouldn't merge it with a previously existing value. See also the same
# test for PutItem - test_put_item_replace().
@@ -210,32 +182,6 @@ def test_batch_write_invalid_operation(test_table_s):
for p in [p1, p2]:
assert not 'item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# In test_item.py we have a bunch of test_empty_* tests on different ways to
# create an empty item (which in Scylla requires the special CQL row marker
# to be supported correctly). BatchWriteItems provides yet another way of
# creating items, so check the empty case here too:
def test_empty_batch_write(test_table):
p = random_string()
c = random_string()
with test_table.batch_writer() as batch:
batch.put_item({'p': p, 'c': c})
assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c}
# Test that BatchWriteItems allows writing to multiple tables in one operation
def test_batch_write_multiple_tables(test_table_s, test_table):
p1 = random_string()
c1 = random_string()
p2 = random_string()
# We use the low-level batch_write_item API for lack of a more convenient
# API (the batch_writer() API can only write to one table). At least it
# spares us the need to encode the key's types...
reply = test_table.meta.client.batch_write_item(RequestItems = {
test_table.name: [{'PutRequest': {'Item': {'p': p1, 'c': c1, 'a': 'hi'}}}],
test_table_s.name: [{'PutRequest': {'Item': {'p': p2, 'b': 'hello'}}}]
})
assert test_table.get_item(Key={'p': p1, 'c': c1}, ConsistentRead=True)['Item'] == {'p': p1, 'c': c1, 'a': 'hi'}
assert test_table_s.get_item(Key={'p': p2}, ConsistentRead=True)['Item'] == {'p': p2, 'b': 'hello'}
# Basic test for BatchGetItem, reading several entire items.
# Schema has both hash and sort keys.
def test_batch_get_item(test_table):
@@ -305,16 +251,3 @@ def test_batch_get_item_projection_expression(test_table):
got_items = reply['Responses'][test_table.name]
expected_items = [{k: item[k] for k in wanted if k in item} for item in items]
assert multiset(got_items) == multiset(expected_items)
# Test that we return the required UnprocessedKeys/UnprocessedItems parameters
def test_batch_unprocessed(test_table_s):
p = random_string()
write_reply = test_table_s.meta.client.batch_write_item(RequestItems = {
test_table_s.name: [{'PutRequest': {'Item': {'p': p, 'a': 'hi'}}}],
})
assert 'UnprocessedItems' in write_reply and write_reply['UnprocessedItems'] == dict()
read_reply = test_table_s.meta.client.batch_get_item(RequestItems = {
test_table_s.name: {'Keys': [{'p': p}], 'ProjectionExpression': 'p, a', 'ConsistentRead': True}
})
assert 'UnprocessedKeys' in read_reply and read_reply['UnprocessedKeys'] == dict()

View File

@@ -22,36 +22,9 @@
# test_condition_expression.py. Many of the tests there are very similar to
# the ones included here.
# NOTE: In this file, we use the b'xyz' syntax to represent DynamoDB's binary
# values. This syntax works as expected only in Python3. In Python2 it
# appears to work, but the "b" is actually ignored and the result is a normal
# string 'xyz'. That means that we end up testing the string type instead of
# the binary type as intended. So this test can run on Python2 but doesn't
# cover testing binary types. The test should be run in Python3 to ensure full
# coverage.
import pytest
from botocore.exceptions import ClientError
from util import random_string
from sys import version_info
# A helper function for changing write isolation policies
def set_write_isolation(table, isolation):
got = table.meta.client.describe_table(TableName=table.name)['Table']
arn = got['TableArn']
tags = [
{
'Key': 'system:write_isolation',
'Value': isolation
}
]
table.meta.client.tag_resource(ResourceArn=arn, Tags=tags)
# A helper function to clear previous isolation tags
def clear_write_isolation(table):
got = table.meta.client.describe_table(TableName=table.name)['Table']
arn = got['TableArn']
table.meta.client.untag_resource(ResourceArn=arn, TagKeys=['system:write_isolation'])
# Most of the tests in this file check that the ConditionExpression
# parameter works for the UpdateItem operation. It should also work the
@@ -88,6 +61,7 @@ def test_condition_expression_attribute_updates(test_table_s):
# attribute from the request, and the case of comparing two different
# attributes of the same item (the latter case wasn't possible to express
# with Expected, and becomes possible with ConditionExpression).
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_eq_success(test_table_s):
p = random_string()
values = (1, "hello", True, b'xyz', None, ['hello', 42], {'hello': 'world'}, set(['hello', 'world']), set([1, 2, 3]), set([b'xyz', b'hi']))
@@ -111,6 +85,7 @@ def test_update_condition_eq_success(test_table_s):
# Comparing values of *different* types should always fail. Check all the
# combination of different types.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_eq_different(test_table_s):
p = random_string()
values = (1, "hello", True, b'xyz', None, ['hello', 42], {'hello': 'world'}, set(['hello', 'world']), set([1, 2, 3]), set([b'xyz', b'hi']))
@@ -137,6 +112,7 @@ def test_update_condition_eq_different(test_table_s):
ExpressionAttributeValues={':val1': val1, ':val2': val2})
# Also check an actual case of same time, but inequality.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_eq_unequal(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -150,6 +126,7 @@ def test_update_condition_eq_unequal(test_table_s):
# Check that set equality is checked correctly. Unlike string equality (for
# example), it cannot be done with just naive string comparison of the JSON
# representation, and we need to allow for any order. (see issue #5021)
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_eq_set(test_table_s):
p = random_string()
# Because boto3 sorts the set values we give it, in order to generate a
@@ -169,6 +146,7 @@ def test_update_condition_eq_set(test_table_s):
assert 'b' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
# Test for ConditionExpression with operator "<>" (non-equality),
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_ne(test_table_s):
p = random_string()
# We only check here one type of attributes (numbers), assuming that the
@@ -209,6 +187,7 @@ def test_update_condition_ne(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == 3
# Test for ConditionExpression with operator "<"
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_lt(test_table_s):
p = random_string()
# The < operator should work for string, number and binary types
@@ -281,6 +260,7 @@ def test_update_condition_lt(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
# Test for ConditionExpression with operator "<="
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_le(test_table_s):
p = random_string()
# The <= operator should work for string, number and binary types
@@ -344,6 +324,7 @@ def test_update_condition_le(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 7
# Test for ConditionExpression with operator ">"
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_gt(test_table_s):
p = random_string()
# The > operator should work for string, number and binary types
@@ -407,6 +388,7 @@ def test_update_condition_gt(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
# Test for ConditionExpression with operator ">="
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_ge(test_table_s):
p = random_string()
# The >= operator should work for string, number and binary types
@@ -472,6 +454,7 @@ def test_update_condition_ge(test_table_s):
# Test for ConditionExpression with ternary operator "BETWEEN" (checking
# if a value is between two others, equality included). The keywords
# "BETWEEN" and "AND" are case insensitive.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_between(test_table_s):
p = random_string()
# The BETWEEN operator should work for string, number and binary types
@@ -553,6 +536,7 @@ def test_update_condition_between(test_table_s):
# Test for ConditionExpression with multi-operand operator "IN", checking
# whether a value is equal to one of possibly many values (up to 100 should
# be supported, according to the DynamoDB documentation).
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_in(test_table_s):
p = random_string()
@@ -599,12 +583,6 @@ def test_update_condition_in(test_table_s):
ConditionExpression='a IN (:x, :y)',
ExpressionAttributeValues={':val': 1, ':x': 'dog', ':y': 174})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == 1
# IN with zero arguments results in a syntax error, not a failed condition
with pytest.raises(ClientError, match='ValidationException.*yntax error'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val37',
ConditionExpression='a IN ()',
ExpressionAttributeValues=values)
# Beyond the above operators, there are also test functions supported -
# attribute_exists, attribute_not_exists, attribute_type, begins_with,
@@ -612,6 +590,7 @@ def test_update_condition_in(test_table_s):
# These functions are listed and described in
# https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Expressions.OperatorsAndFunctions.html
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_attribute_exists(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -626,34 +605,8 @@ def test_update_condition_attribute_exists(test_table_s):
UpdateExpression='SET c = :val',
ConditionExpression='attribute_exists (z)',
ExpressionAttributeValues={':val': 3})
# Somewhat artificially, attribute_exists() requires that its parameter
# be a path - it cannot be a different sort of value.
with pytest.raises(ClientError, match='ValidationException.*path'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='attribute_exists (:val)',
ExpressionAttributeValues={':val': 3})
# Primitive conditions usually look like an operator between two (<, <=,
# etc.), three (BETWEEN) or more (IN) values. Can just a single value be
# a condition? The special case of a single function call *can* be - we saw
# an example attribute_exists(z) in the previous test. However that only
# function calls are supported in this context - not general values (i.e.,
# attribute or value references).
# While DynamoDB does not accept a non-function-call value as a condition
# (it results with with a syntax error), in Alternator currently, for
# simplicity of the parser, this case is parsed correctly and only fails
# later when the calculated value ends up to not be a boolean.
def test_update_condition_single_value_attribute(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='a',
ExpressionAttributeValues={':val': 1})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_attribute_not_exists(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -669,6 +622,7 @@ def test_update_condition_attribute_not_exists(test_table_s):
ConditionExpression='attribute_not_exists (a)',
ExpressionAttributeValues={':val': 3})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_attribute_type(test_table_s):
p = random_string()
type_values = [
@@ -686,10 +640,6 @@ def test_update_condition_attribute_type(test_table_s):
test_table_s.update_item(Key={'p': p}, AttributeUpdates=updates)
for i in range(len(type_values)):
expected_type = type_values[i][0]
# As explained in a comment in the top of the file, the binary types
# cannot be tested with Python 2
if expected_type in ('B', 'BS') and version_info[0] == 2:
continue
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='attribute_type (a{}, :type)'.format(i),
@@ -701,43 +651,25 @@ def test_update_condition_attribute_type(test_table_s):
UpdateExpression='SET c = :val',
ConditionExpression='attribute_type (a{}, :type)'.format(i),
ExpressionAttributeValues={':val': i, ':type': wrong_type})
# The DynamoDB documentation suggests that attribute_type()'s first
# parameter must be a path (as we saw above, this is indeed the case for
# attribute_exists()). But in fact, attribute_type() does work fine also
# for an expression attribute.
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='attribute_type (:val, :type)',
ExpressionAttributeValues={':val': 0, ':type': 'N'})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == 0
# The DynamoDB documentation explicitly states that the second argument
# of the attribute_type function - the type to compare to - *must* be an
# expression attribute (:name) - it cannot be an item attribute.
# I don't know why this was important to forbid, but this test confirms that
# DynamoDB does forbid it.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_attribute_type_second_arg(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
'b': {'Value': 'N', 'Action': 'PUT'}})
with pytest.raises(ClientError, match='ValidationException'):
with pytest.raises(ClientError, match='ValidationException.*Incorrect'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='attribute_type (a, b)',
ExpressionAttributeValues={':val': 1})
# If the attribute_type() parameter is not one of the known types
# (N,NS,BS,L,SS,NULL,B,BOOL,S,M), an error is generated. We should
# not get a failed condition.
def test_update_condition_attribute_type_unknown(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException.*DOG'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='attribute_type (a, :type)',
ExpressionAttributeValues={':val': 1, ':type': 'DOG'})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_begins_with(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -766,11 +698,6 @@ def test_update_condition_begins_with(test_table_s):
UpdateExpression='SET c = :val',
ConditionExpression='begins_with(a, :arg)',
ExpressionAttributeValues={':val': 3, ':arg': 2})
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='begins_with(c, :arg)',
ExpressionAttributeValues={':val': 3, ':arg': 2})
# However, that extra type check is only done on values inside the
# expression. It isn't done on values from an item attributes - in that
# case we got a normal failed condition.
@@ -784,34 +711,19 @@ def test_update_condition_begins_with(test_table_s):
UpdateExpression='SET c = :val',
ConditionExpression='begins_with(c, a)',
ExpressionAttributeValues={':val': 3})
# Although the DynamoDB documentation suggests that begins_with()
# can only take a path as the first parameter and a constant as
# the second, this isn't actually true - begins_with() works
# as expected also to compare two attributes, or in reverse order:
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='begins_with(:str, a)',
ExpressionAttributeValues={':val': 'he', ':str': 'hellohi'})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == 'he'
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET c = :val',
ConditionExpression='begins_with(a, c)',
ExpressionAttributeValues={':val': 5})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == 5
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_contains(test_table_s):
p = random_string()
# contains() can be used for two unrelated things: check substring (in
# string or binary) and membership (in set or a list). The DynamoDB
# documentation only mention string and set (not binary or list) but
# documentation only bention string and set (not binary or list) but
# the fact is that binary and list are also support.
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'},
'b': {'Value': set([2, 4, 7]), 'Action': 'PUT'},
'c': {'Value': [2, 4, 7], 'Action': 'PUT'},
'd': {'Value': b'hi there', 'Action': 'PUT'},
'e': {'Value': ['hi', set([1,2]), [3, 4]], 'Action': 'PUT'}})
'd': {'Value': b'hi there', 'Action': 'PUT'}})
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='contains(a, :arg)',
@@ -840,37 +752,11 @@ def test_update_condition_contains(test_table_s):
UpdateExpression='SET z = :val',
ConditionExpression='contains(d, :arg)',
ExpressionAttributeValues={':val': 4, ':arg': b'dog'})
# Moreover, the second parameter to contains() may be *any* type, and
# contains checks if perhaps the first parameter is a list or a set
# containing that value!
with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='contains(d, :arg)',
ExpressionAttributeValues={':val': 4, ':arg': set([1, 2])})
# While both operands of contains may be item attributes, strangely
# it is explicitly forbidden to have the same attribute as both and
# trying to do so results in a ValidationException.
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='contains(e, :arg)',
ExpressionAttributeValues={':val': 5, ':arg': set([1, 2])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 5
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='contains(e, :arg)',
ExpressionAttributeValues={':val': 6, ':arg': [3, 4]})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 6
# While both operands of contains() may be item attributes, strangely
# it is explicitly forbidden to have the same attribute as both and
# trying to do so results in a ValidationException. I don't know why it's
# important to make this query fail, when it could have just worked...
# TODO: Is this limitation only for contains() or other functions as well?
@pytest.mark.xfail(reason="extra check for same attribute not implemented yet")
def test_update_condition_contains_same_attribute(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a1': {'Value': 'hello', 'Action': 'PUT'},
'a': {'Value': 'hello', 'Action': 'PUT'}})
AttributeUpdates={'a1': {'Value': 'hello', 'Action': 'PUT'}})
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='contains(a, a1)',
@@ -888,6 +774,7 @@ def test_update_condition_contains_same_attribute(test_table_s):
# function whose return value needs to be further combined with another
# operand using a comparison operation - and it isn't specified which is
# supported.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_size(test_table_s):
p = random_string()
# First verify what size() returns for various types. We use only the
@@ -897,7 +784,7 @@ def test_update_condition_size(test_table_s):
'b': {'Value': set([2, 4, 7]), 'Action': 'PUT'},
'c': {'Value': [2, 'dog', 7], 'Action': 'PUT'},
'd': {'Value': b'hi there', 'Action': 'PUT'},
'e': {'Value': {'x': 2, 'y': {'m': 3, 'n': 4}}, 'Action': 'PUT'},
'e': {'Value': {'x': 2, 'y': 3}, 'Action': 'PUT'},
'f': {'Value': 5, 'Action': 'PUT'},
'g': {'Value': True, 'Action': 'PUT'},
'h': {'Value': None, 'Action': 'PUT'}})
@@ -982,70 +869,6 @@ def test_update_condition_size(test_table_s):
ConditionExpression='size(a)>=:arg',
ExpressionAttributeValues={':val': 11, ':arg': 2})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 11
# size() is only allowed one operand; More operands are allowed by the
# parser, but later result in an error:
with pytest.raises(ClientError, match='ValidationException.*2'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='size(a, a)=:arg',
ExpressionAttributeValues={':val': 1, ':arg': 5})
# The above test tested conditions involving size() in a comparison.
# Trying to use just size(a) as a condition (as we use the rest of the
# functions supported by ConditionExpression) does not work - DynamoDB
# reports # that "The function is not allowed to be used this way in an
# expression; function: size".
def test_update_condition_size_alone(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='size(a)',
ExpressionAttributeValues={':val': 1})
# Similarly, while attribute_exists(a) works alone, it cannot be used in
# a comparison, e.g., attribute_exists(a) < 1 also causes DynamoDB to
# complain about "The function is not allowed to be used in this way in an
# expression.".
def test_update_condition_attribute_exists_in_comparison(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='attribute_exists(a) < :val',
ExpressionAttributeValues={':val': 1})
# In essense, the size() function tested in the previous test behaves
# exactly like the functions of UpdateExpressions, i.e., it transforms a
# value (attribute from the item or the query) into a new value, which
# can than be operated (in our case, compared). In this test we check
# that other functions supported by UpdateExpression - if_not_exists()
# and list_append() - are not supported.
def test_update_condition_other_funcs(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'}})
# dog() is an unknown function name:
with pytest.raises(ClientError, match='ValidationException.*function'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='dog(a)=:arg',
ExpressionAttributeValues={':val': 1, ':arg': 5})
# The functions if_not_exists() and list_append() are known functions
# (they are supported in UpdateExpression) but not allowed in
# ConditionExpression. This means we can have a single function for
# evaluation a parsed::value, but it needs to know whether it is
# called for a UpdateExpression or a ConditionExpression.
with pytest.raises(ClientError, match='ValidationException.*not allowed'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='if_not_exists(a, a)=:arg',
ExpressionAttributeValues={':val': 1, ':arg': 5})
with pytest.raises(ClientError, match='ValidationException.*not allowed'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='list_append(a, a)=:arg',
ExpressionAttributeValues={':val': 1, ':arg': 5})
# All the previous tests involved top-level attributes to be tested. But
# ConditionExpressions also allows reading nested attributes, and we should
@@ -1071,6 +894,7 @@ def test_update_condition_nested_attributes(test_table_s):
# But the DynamoDB API also allows to refer to attributes using a #reference.
# Among other things this allows using attribute names which are usually
# reserved keywords in condition expressions.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_attribute_reference(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1100,6 +924,7 @@ def test_update_condition_nested_attribute_reference(test_table_s):
# precedence involved, and should be tested (see the definitions in
# https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Expressions.OperatorsAndFunctions.html
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_and(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1124,6 +949,7 @@ def test_update_condition_and(test_table_s):
ConditionExpression='a < b AND c < b',
ExpressionAttributeValues={':val': 1})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_or(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1153,6 +979,7 @@ def test_update_condition_or(test_table_s):
ConditionExpression='b < a OR c < b',
ExpressionAttributeValues={':val': 1})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_not(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1175,13 +1002,8 @@ def test_update_condition_not(test_table_s):
UpdateExpression='SET z = :val',
ConditionExpression='NOT a < b',
ExpressionAttributeValues={':val': 1})
# NOT NOT NOT NOT also works (and does nothing) :-)
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :val',
ConditionExpression='NOT NOT NOT NOT a < b',
ExpressionAttributeValues={':val': 3})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 3
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_parentheses(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1197,6 +1019,7 @@ def test_update_condition_parentheses(test_table_s):
# There is operator precedence that allows a user to use less parentheses.
# We need to implement it correctly:
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_and_before_or(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1209,6 +1032,7 @@ def test_update_condition_and_before_or(test_table_s):
ExpressionAttributeValues={':val': 1})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 1
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_not_before_and(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1221,6 +1045,7 @@ def test_update_condition_not_before_and(test_table_s):
ConditionExpression='NOT a < b AND c < b',
ExpressionAttributeValues={':val': 1})
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_between_before_and(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1235,6 +1060,7 @@ def test_update_condition_between_before_and(test_table_s):
# An empty ConditionExpression is not allowed - resulting in a validation
# error, not a failed condition:
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_update_condition_empty(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException.*empty'):
@@ -1250,6 +1076,7 @@ def test_update_condition_empty(test_table_s):
# used to test the condition. So we just need one test for each operation,
# to verify that this code actually gets called.
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_delete_item_condition(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1264,6 +1091,7 @@ def test_delete_item_condition(test_table_s):
ExpressionAttributeValues={':oldval': 1})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
def test_put_item_condition(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
@@ -1276,222 +1104,3 @@ def test_put_item_condition(test_table_s):
test_table_s.put_item(Item={'p': p, 'a': 3},
ConditionExpression='a = :oldval',
ExpressionAttributeValues={':oldval': 1})
# DynamoDB frowns upon unused entries in ExpressionAttributeValues and
# ExpressionAttributeNames. Check that we do too (in all three operations),
# although it's not terribly important that we be compatible with DynamoDB
# here...
# There's one delicate issue, though. Should we check for unused entries
# during parsing, or during evaluation? The stage we check this changes
# our behavior when the condition was supposed to fail. So we have two
# separate tests here, one for failed condition and one for successful.
def test_update_condition_unused_entries_failed(test_table_s):
p = random_string()
# unused val3:
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET #name1 = :val1',
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val1': 1, ':val2': 2, ':val3': 3},
ExpressionAttributeNames={'#name1': 'a', '#name2': 'b'})
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.delete_item(Key={'p': p},
ConditionExpression='#name1 = :val1',
ExpressionAttributeValues={':val1': 1, ':val3': 3},
ExpressionAttributeNames={'#name1': 'a'})
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.put_item(Item={'p': p, 'a': 3},
ConditionExpression='#name1 = :val1',
ExpressionAttributeValues={':val1': 1, ':val3': 3},
ExpressionAttributeNames={'#name1': 'a'})
# unused name3:
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET #name1 = :val1',
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val1': 1, ':val2': 2},
ExpressionAttributeNames={'#name1': 'a', '#name2': 'b', '#name3': 'c'})
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.delete_item(Key={'p': p},
ConditionExpression='#name1 = :val1',
ExpressionAttributeValues={':val1': 1},
ExpressionAttributeNames={'#name1': 'a', '#name3': 'c'})
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.put_item(Item={'p': p, 'a': 3},
ConditionExpression='#name1 = :val1',
ExpressionAttributeValues={':val1': 1},
ExpressionAttributeNames={'#name1': 'a', '#name3': 'c'})
def test_update_condition_unused_entries_succeeded(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}})
# unused val3:
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET #name1 = :val1',
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val1': 1, ':val2': 2, ':val3': 3},
ExpressionAttributeNames={'#name1': 'a', '#name2': 'b'})
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.delete_item(Key={'p': p},
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val2': 2, ':val3': 3},
ExpressionAttributeNames={'#name2': 'b'})
with pytest.raises(ClientError, match='ValidationException.*val3'):
test_table_s.put_item(Item={'p': p, 'a': 3},
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val2': 2, ':val3': 3},
ExpressionAttributeNames={'#name2': 'b'})
# unused name3:
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET #name1 = :val1',
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val1': 1, ':val2': 2},
ExpressionAttributeNames={'#name1': 'a', '#name2': 'b', '#name3': 'c'})
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.delete_item(Key={'p': p},
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val2': 2},
ExpressionAttributeNames={'#name2': 'b', '#name3': 'c'})
with pytest.raises(ClientError, match='ValidationException.*name3'):
test_table_s.put_item(Item={'p': p, 'a': 3},
ConditionExpression='#name2 = :val2',
ExpressionAttributeValues={':val2': 2},
ExpressionAttributeNames={'#name2': 'b', '#name3': 'c'})
# Another reason why we must test for used references right after parsing
# the expressions, NOT at evaluation time, is that in some cases evaluation
# may short-circuit and not reach certain parts of the expression, and as
# a result we may wrongly think some names were not used, and refuse a
# perfectly good request. Such a bug (see issue #6572) can be fixed by
# either by dropping short-circuit evaluation (i.e., evaluate all parts
# of the expression even if the first OR succeeds), or by testing for
# unused references before evaluating anything.
def test_update_condition_unused_entries_short_circuit(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
# If short-circuit evaluation is done for ConditionExpression, it will
# not use #name2 or :val2. But we should't fail this request claiming
# these references weren't used... They were used in the expression,
# just not in the evaluation. This request *should* work.
test_table_s.update_item(Key={'p': p},
ConditionExpression='#name1 = :val1 OR #name2 = :val2',
UpdateExpression='SET #name1 = :val3',
ExpressionAttributeValues={':val1': 1, ':val2': 2, ':val3': 3},
ExpressionAttributeNames={'#name1': 'a', '#name2': 'b'})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 3}
# Test a bunch of cases with permissive write isolation levels,
# i.e. LWT_ALWAYS, LWT_RMW_ONLY and UNSAFE_RMW.
# These test cases make sense only for alternator, so they're skipped
# when run on AWS
def test_condition_expression_with_permissive_write_isolation(scylla_only, dynamodb, test_table_s):
def do_test_with_permissive_isolation_levels(test_case, table, *args):
try:
for isolation in ['a', 'o', 'u']:
set_write_isolation(table, isolation)
test_case(table, *args)
finally:
clear_write_isolation(table)
for test_case in [test_update_condition_eq_success, test_update_condition_attribute_exists,
test_delete_item_condition, test_put_item_condition, test_update_condition_attribute_reference]:
do_test_with_permissive_isolation_levels(test_case, test_table_s)
# Test that the forbid_rmw isolation level prevents read-modify-write requests
# from working. These test cases make sense only for alternator, so they're skipped
# when run on AWS
def test_condition_expression_with_forbidden_rmw(scylla_only, dynamodb, test_table_s):
def do_test_with_forbidden_rmw(test_case, table, *args):
try:
set_write_isolation(table, 'f')
test_case(table, *args)
assert False, "Expected an exception when running {}".format(test_case.__name__)
except ClientError:
pass
finally:
clear_write_isolation(table)
for test_case in [test_update_condition_eq_success, test_update_condition_attribute_exists,
test_put_item_condition, test_update_condition_attribute_reference]:
do_test_with_forbidden_rmw(test_case, test_table_s)
# Ensure that regular writes (without rmw) work just fine
s = random_string()
test_table_s.put_item(Item={'p': s, 'regular': 'write'})
assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'regular': 'write'}
test_table_s.update_item(Key={'p': s}, AttributeUpdates={'write': {'Value': 'regular', 'Action': 'PUT'}})
assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'regular': 'write', 'write': 'regular'}
# Reproducer for issue #6573: binary strings should be ordered as unsigned
# bytes, i.e., byte 128 comes after 127, not before as with signed bytes.
# Test the five ordering operators: <, <=, >, >=, between
def test_condition_expression_unsigned_bytes(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'b': bytearray([127])})
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :newval',
ConditionExpression='b < :oldval',
ExpressionAttributeValues={':newval': 1, ':oldval': bytearray([128])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 1
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :newval',
ConditionExpression='b <= :oldval',
ExpressionAttributeValues={':newval': 2, ':oldval': bytearray([128])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 2
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :newval',
ConditionExpression='b between :oldval1 and :oldval2',
ExpressionAttributeValues={':newval': 3, ':oldval1': bytearray([126]), ':oldval2': bytearray([128])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 3
test_table_s.put_item(Item={'p': p, 'b': bytearray([128])})
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :newval',
ConditionExpression='b > :oldval',
ExpressionAttributeValues={':newval': 4, ':oldval': bytearray([127])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET z = :newval',
ConditionExpression='b >= :oldval',
ExpressionAttributeValues={':newval': 5, ':oldval': bytearray([127])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 5
# In all other tests above, we use ConditionExpression to check a condition
# on one the non-key attributes. In this test we confirm that a condition may
# also be on a key attribute. We demonstrate this through a useful DynamoDB
# idiom for creating an item unless an item already exists with the same key,
# by using a "<>" (not equal) condition.
def test_update_item_condition_key_ne(test_table_s):
p = random_string()
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# Create an empty item with key p, but only an item with p exists yet.
# Note how when the item does not exist, the <> (not equal) test succeeds
# (we already tested that in test_update_condition_ne())
test_table_s.update_item(Key={'p': p},
ConditionExpression='p <> :p',
ExpressionAttributeValues={':p': p})
assert 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# If we do the same again, the item does exist, and the <> condition will
# fail.
with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
test_table_s.update_item(Key={'p': p},
ConditionExpression='p <> :p',
ExpressionAttributeValues={':p': p})
# Another example of a condition on the key, again an idiom for creating an
# item if no item already has that key. This time, using the
# attribute_not_exists() instead of the <> (not equal) operator in the test
# above.
def test_update_item_condition_key_attribute_not_exists(test_table_s):
p = random_string()
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# Create an empty item with key p, but only an item with p exists yet.
# Note how when the item does not exist, attribute_not_exists() succeeds
test_table_s.update_item(Key={'p': p},
ConditionExpression='attribute_not_exists(p)')
assert 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# If we do the same again, the item does exist, and the
# attribute_not_exists() condition will fail.
with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
test_table_s.update_item(Key={'p': p},
ConditionExpression='attribute_not_exists(p)')

View File

@@ -141,16 +141,19 @@ def test_describe_table_stream_specification(test_table):
# includes which zone it is on, which account, and of course the table's
# name. The ARN format is described in
# https://docs.aws.amazon.com/general/latest/gr/aws-arns-and-namespaces.html#genref-arns
@pytest.mark.xfail(reason="DescribeTable does not return ARN")
def test_describe_table_arn(test_table):
got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
assert 'TableArn' in got and got['TableArn'].startswith('arn:')
# Test that the table has a TableId.
# DynamoDB documentation states that this id must look like a UUID.
# TODO: Figure out what is this TableId supposed to be, it is just a
# unique id that is created with the table and never changes? Or anything
# else?
@pytest.mark.xfail(reason="DescribeTable does not return TableId")
def test_describe_table_id(test_table):
got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
assert 'TableId' in got
assert re.fullmatch('[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}', got['TableId'])
# DescribeTable error path: trying to describe a non-existent table should
# result in a ResourceNotFoundException.

View File

@@ -522,15 +522,6 @@ def test_update_expected_1_null(test_table_s):
Expected={'a': {'ComparisonOperator': 'NULL', 'AttributeValueList': [2]}}
)
# When ComparisonOperator = "NULL", AttributeValueList should be empty if it
# exists, but as this test verifies, it may also be missing completely.
def test_update_expected_1_null_missing_list(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'}},
Expected={'a': {'ComparisonOperator': 'NULL'}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
# Tests for Expected with ComparisonOperator = "CONTAINS":
def test_update_expected_1_contains(test_table_s):
# true cases. CONTAINS can be used for two unrelated things: check substrings
@@ -607,10 +598,6 @@ def test_update_expected_1_contains(test_table_s):
AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
Expected={'a': {'ComparisonOperator': 'CONTAINS', 'AttributeValueList': []}}
)
# Strangely, while ConditionExpression's contains() allows the argument
# to be of any type and checks if the attribute is perhaps a list
# containing that item, Expected's "CONTAINS" is more limited, and
# refuses a list as the argument (to be searched in a list of lists)
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -697,10 +684,6 @@ def test_update_expected_1_not_contains(test_table_s):
AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
Expected={'a': {'ComparisonOperator': 'NOT_CONTAINS', 'AttributeValueList': []}}
)
# Strangely, while ConditionExpression's contains() allows the argument
# to be of any type and checks if the attribute is perhaps a list
# containing that item, Expected's "CONTAINS" is more limited, and
# refuses a list as the argument (to be searched in a list of lists)
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -1069,19 +1052,6 @@ def test_update_expected_empty(test_table_s):
AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
Expected={}, ConditionalOperator='AND')
# Specifying ConditionalOperator is forbidden if the "Expected" Attribute
# is missing:
def test_conditional_operator_expected_missing(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
ConditionalOperator='OR')
with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
ConditionalOperator='AND')
# All of the above tests tested "Expected" with the UpdateItem operation.
# We now want to test that it works also with the PutItem and DeleteItems
# operations. We don't need to check again all the different sub-cases tested
@@ -1107,42 +1077,3 @@ def test_put_item_expected(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 2}
with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
test_table_s.put_item(Item={'p': p, 'a': 3}, Expected={'a': {'Value': 1}})
# Reproducer for issue #6573: binary strings should be ordered as unsigned
# bytes, i.e., byte 128 comes after 127, not before as with signed bytes.
# Test the five ordering operators: LT, LE, GT, GE, BETWEEN
def test_update_expected_unsigned_bytes(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'b': bytearray([127])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 1, 'Action': 'PUT'}},
Expected={'b': {'ComparisonOperator': 'LT',
'AttributeValueList': [bytearray([128])]}}
)
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 1
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
Expected={'b': {'ComparisonOperator': 'LE',
'AttributeValueList': [bytearray([128])]}}
)
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 2
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
Expected={'b': {'ComparisonOperator': 'BETWEEN',
'AttributeValueList': [bytearray([126]), bytearray([128])]}}
)
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 3
test_table_s.put_item(Item={'p': p, 'b': bytearray([128])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
Expected={'b': {'ComparisonOperator': 'GT',
'AttributeValueList': [bytearray([127])]}}
)
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'z': {'Value': 5, 'Action': 'PUT'}},
Expected={'b': {'ComparisonOperator': 'GE',
'AttributeValueList': [bytearray([127])]}}
)
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 5

View File

@@ -37,25 +37,22 @@ from util import create_test_table, random_string, full_scan, full_query, multis
# retry.
def assert_index_query(table, index_name, expected_items, **kwargs):
for i in range(3):
if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, ConsistentRead=False, **kwargs)):
if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
return
print('assert_index_query retrying')
time.sleep(1)
assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, ConsistentRead=False, **kwargs))
assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
def assert_index_scan(table, index_name, expected_items, **kwargs):
for i in range(3):
if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, ConsistentRead=False, **kwargs)):
if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
return
print('assert_index_scan retrying')
time.sleep(1)
assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, ConsistentRead=False, **kwargs))
assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
# Although quite silly, it is actually allowed to create an index which is
# identical to the base table.
# The following test does not work for KA/LA tables due to #6157,
# so it's hereby skipped.
@pytest.mark.skip
def test_gsi_identical(dynamodb):
table = create_test_table(dynamodb,
KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
@@ -74,9 +71,9 @@ def test_gsi_identical(dynamodb):
# results (in different order).
assert multiset(items) == multiset(full_scan(table))
assert_index_scan(table, 'hello', items)
# We can't scan a non-existent index
# We can't scan a non-existant index
with pytest.raises(ClientError, match='ValidationException'):
full_scan(table, ConsistentRead=False, IndexName='wrong')
full_scan(table, IndexName='wrong')
table.delete()
# One of the simplest forms of a non-trivial GSI: The base table has a hash
@@ -153,18 +150,13 @@ def test_gsi_missing_table(dynamodb):
dynamodb.meta.client.scan(TableName='nonexistent_table', IndexName='any_name')
# Verify that strongly-consistent reads on GSI are *not* allowed.
@pytest.mark.xfail(reason="GSI strong consistency not checked")
def test_gsi_strong_consistency(test_table_gsi_1):
with pytest.raises(ClientError, match='ValidationException.*Consistent'):
full_query(test_table_gsi_1, KeyConditions={'c': {'AttributeValueList': ['hi'], 'ComparisonOperator': 'EQ'}}, IndexName='hello', ConsistentRead=True)
with pytest.raises(ClientError, match='ValidationException.*Consistent'):
full_scan(test_table_gsi_1, IndexName='hello', ConsistentRead=True)
# Test that setting an indexed string column to an empty string is illegal,
# since keys cannot contain empty strings
def test_gsi_empty_value(test_table_gsi_2):
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_gsi_2.put_item(Item={'p': random_string(), 'x': ''})
# Verify that a GSI is correctly listed in describe_table
@pytest.mark.xfail(reason="DescribeTable provides index names only, no size or item count")
def test_gsi_describe(test_table_gsi_1):
@@ -295,8 +287,8 @@ def test_gsi_missing_attribute(test_table_gsi_2):
test_table_gsi_2.put_item(Item={'p': p2})
# Both items are now in the base table:
assert test_table_gsi_2.get_item(Key={'p': p1}, ConsistentRead=True)['Item'] == {'p': p1, 'x': x1}
assert test_table_gsi_2.get_item(Key={'p': p2}, ConsistentRead=True)['Item'] == {'p': p2}
assert test_table_gsi_2.get_item(Key={'p': p1})['Item'] == {'p': p1, 'x': x1}
assert test_table_gsi_2.get_item(Key={'p': p2})['Item'] == {'p': p2}
# But only the first item is in the index: It can be found using a
# Query, and a scan of the index won't find it (but a scan on the base
@@ -308,7 +300,7 @@ def test_gsi_missing_attribute(test_table_gsi_2):
# and item will "never" appear in the index. We do this test last,
# so if we had a bug and such item did appear, hopefully we had enough
# time for the bug to become visible. At least sometimes.
assert not any([i['p'] == p2 for i in full_scan(test_table_gsi_2, ConsistentRead=False, IndexName='hello')])
assert not any([i['p'] == p2 for i in full_scan(test_table_gsi_2, IndexName='hello')])
# Test when a table has a GSI, if the indexed attribute has the wrong type,
# the update operation is rejected, and is added to neither base table nor
@@ -410,20 +402,20 @@ def test_gsi_missing_attribute_3(test_table_gsi_3):
# First, add an item with a missing "a" value. It should appear in the
# base table, but not in the index:
test_table_gsi_3.put_item(Item={'p': p, 'b': b})
assert test_table_gsi_3.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': b}
assert test_table_gsi_3.get_item(Key={'p': p})['Item'] == {'p': p, 'b': b}
# Note: with eventually consistent read, we can't really be sure that
# an item will "never" appear in the index. We hope that if a bug exists
# and such an item did appear, sometimes the delay here will be enough
# for the unexpected item to become visible.
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, ConsistentRead=False, IndexName='hello')])
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, IndexName='hello')])
# Same thing for an item with a missing "b" value:
test_table_gsi_3.put_item(Item={'p': p, 'a': a})
assert test_table_gsi_3.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': a}
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, ConsistentRead=False, IndexName='hello')])
assert test_table_gsi_3.get_item(Key={'p': p})['Item'] == {'p': p, 'a': a}
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, IndexName='hello')])
# And for an item missing both:
test_table_gsi_3.put_item(Item={'p': p})
assert test_table_gsi_3.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, ConsistentRead=False, IndexName='hello')])
assert test_table_gsi_3.get_item(Key={'p': p})['Item'] == {'p': p}
assert not any([i['p'] == p for i in full_scan(test_table_gsi_3, IndexName='hello')])
# A fourth scenario of GSI. Two GSIs on a single base table.
@pytest.fixture(scope="session")
@@ -735,10 +727,10 @@ def test_gsi_backfill(dynamodb):
# assert_index_scan() or assert_index_query() functions) because after
# we waited for backfilling to complete, we know all the pre-existing
# data is already in the index.
assert multiset(items1) == multiset(full_scan(table, ConsistentRead=False, IndexName='hello'))
assert multiset(items1) == multiset(full_scan(table, IndexName='hello'))
# We can also use Query on the new GSI, to search on the attribute x:
assert multiset([items1[3]]) == multiset(full_query(table,
ConsistentRead=False, IndexName='hello',
IndexName='hello',
KeyConditions={'x': {'AttributeValueList': [items1[3]['x']], 'ComparisonOperator': 'EQ'}}))
# Let's also test that we cannot add another index with the same name
# that already exists
@@ -785,7 +777,7 @@ def test_gsi_delete(dynamodb):
wait_for_gsi_gone(table, 'hello')
# Now index is gone. We cannot query using it.
with pytest.raises(ClientError, match='ValidationException.*hello'):
full_query(table, ConsistentRead=False, IndexName='hello',
full_query(table, IndexName='hello',
KeyConditions={'x': {'AttributeValueList': [items[3]['x']], 'ComparisonOperator': 'EQ'}})
table.delete()

View File

@@ -22,7 +22,7 @@ import requests
# Test that a health check can be performed with a GET packet
def test_health_works(dynamodb):
url = dynamodb.meta.client._endpoint.host
response = requests.get(url, verify=False)
response = requests.get(url)
assert response.ok
assert response.content.decode('utf-8').strip() == 'healthy: {}'.format(url.replace('https://', '').replace('http://', ''))

View File

@@ -151,14 +151,14 @@ def test_basic_string_more_update(test_table):
assert item['a2'] == val2
assert not 'a3' in item
# Test that item operations on a non-existent table name fail with correct
# Test that item operations on a non-existant table name fail with correct
# error code.
def test_item_operations_nonexistent_table(dynamodb):
with pytest.raises(ClientError, match='ResourceNotFoundException'):
dynamodb.meta.client.put_item(TableName='non_existent_table',
Item={'a':{'S':'b'}})
# Fetching a non-existent item. According to the DynamoDB doc, "If there is no
# Fetching a non-existant item. According to the DynamoDB doc, "If there is no
# matching item, GetItem does not return any data and there will be no Item
# element in the response."
def test_get_item_missing_item(test_table):
@@ -400,282 +400,3 @@ def test_put_item_replace(test_table_s, test_table):
assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 'hi'}
test_table.put_item(Item={'p': p, 'c': c, 'b': 'hello'})
assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'b': 'hello'}
# Test what UpdateItem does on a non-existent item. An operation that puts an
# attribute, creates this item. Even an empty operation creates an item
# (this is test_empty_update() above). But an operation that only deletes
# attributes, does not create an empty item. This reproduces issue #5862.
def test_update_item_non_existent(test_table_s):
# An update that puts an attribute on a non-existent item, creates it:
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 3, 'Action': 'PUT'}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 3}
# An update that does *nothing* on a non-existent item, still creates it:
p = random_string()
test_table_s.update_item(Key={'p': p}, AttributeUpdates={})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
# HOWEVER, an update that only deletes an attribute on a non-existent
# item, does NOT creates it: (issue #5862 was about Alternator wrongly
# creating and empty item in this case).
p = random_string()
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE'}})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# Test the same thing - that an attribute-deleting update does not
# create a non-existing item - but now with the update expression syntax:
p = random_string()
test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a')
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# UpdateItem's AttributeUpdate's DELETE operations has two different
# meanings. It can be used to delete an entire attribute, but can also be
# used to delete elements from a set attribute. The latter is a RMW operation,
# because it requires testing the existing value of the attribute, if it
# is indeed a set of the desired type.
@pytest.mark.xfail(reason="UpdateItem AttributeUpdates DELETE not implemented for sets")
def test_update_item_delete(test_table_s):
p = random_string()
a = random_string()
test_table_s.put_item(Item={'p': p, 'a': a})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': a}
# An Value-less DELETE just deletes the entire attribute
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE'}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
# The "Value" parameter is rejected for *most* types, except sets.
# Even lists (supported by the ADD operation) are rejected.
for value in ['b', 3, bytearray('b', 'utf-8'), True, False, None,
[2,3], {'a': 3}]:
test_table_s.put_item(Item={'p': p, 'a': value})
with pytest.raises(ClientError, match='ValidationException.*type'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': value}})
# "Value" is allowed for sets, but the existing content of the attribute
# must be a set as well, otherwise we get an error on mismatched type
with pytest.raises(ClientError, match='ValidationException.*mismatch'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([1, 2])}})
# When "Value" is a set and the attribute is a set of the same type,
# DELETE remove these items from the set attribute. It works on all
# three set types (string, bytes, number):
test_table_s.put_item(Item={'p': p, 'a': set([1, 2, 3, 4, 5])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([2, 4])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 3, 5])}
test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'lion'])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set(['dog'])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set(['cat', 'lion'])}
test_table_s.put_item(Item={'p': p, 'a': set([b'dog', b'cat', b'lion'])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([b'cat'])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([b'dog', b'lion'])}
# If the item and value are both sets, but not of the same type, we
# get an error on the mismatched types:
test_table_s.put_item(Item={'p': p, 'a': set([1, 2, 3, 4, 5])})
with pytest.raises(ClientError, match='ValidationException.*mismatch'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set(['hi'])}})
# An empty set is not allowed as Value:
test_table_s.put_item(Item={'p': p, 'a': set([1, 2, 3])})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([])}})
# Deleting all the elments from a set doesn't leave an empty set
# (which DynamoDB doesn't allow) but rather deletes the attribute:
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([1, 2, 3])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
# Removing an item not already in the set is fine, and ignores it:
test_table_s.put_item(Item={'p': p, 'a': set([1, 2, 3])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([4])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 2, 3])}
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([2, 5])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 3])}
# Asking to delete an attribute or parts of a set attribute is silently
# ignored if the item doesn't exist (no error, and item isn't created).
p = random_string()
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE'}})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'DELETE', 'Value': set([4])}})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# Test for UpdateItem's AttributeUpdate's ADD operation, which has different
# meanings for numbers and sets - but not for other types.
@pytest.mark.xfail(reason="UpdateItem AttributeUpdates ADD not implemented")
def test_update_item_add(test_table_s):
p = random_string()
# ADD operations on numbers:
test_table_s.put_item(Item={'p': p, 'a': 7})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': 2}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 9}
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': Decimal(-3.5)}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': Decimal(5.5)}
# Incrementing a non-existent attribute is allowed (as if the value is 0)
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'b': {'Action': 'ADD', 'Value': 2}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': Decimal(5.5), 'b': 2}
# ADD operation on sets:
test_table_s.put_item(Item={'p': p, 'a': set([1, 2])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': set([3, 4])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 2, 3, 4])}
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': set([3, 5])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 2, 3, 4, 5])}
# Adding a set to a non-existent attribute is allowed (as if empty set)
# The DynamoDB documentation suggests this is only allowed for a set
# of numbers, but it actually works for any set type.
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'b': {'Action': 'ADD', 'Value': set([7])}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'c': {'Action': 'ADD', 'Value': set(['a', 'b'])}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': set([1, 2, 3, 4, 5]), 'b': set([7]), 'c': set(['a', 'b'])}
# The set type in the attribute and the Value argument needs to match:
with pytest.raises(ClientError, match='ValidationException.*mismatch'):
test_table_s.put_item(Item={'p': p, 'a': set([1, 2])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': set(['a'])}})
# ADD operation on lists (not documented, but works similar to sets!)
test_table_s.put_item(Item={'p': p, 'a': [1, 2]})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': [3, 4]}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [1, 2, 3, 4]}
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': [3, 5]}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [1, 2, 3, 4, 3, 5]}
# Adding a list to a non-existent attribute is allowed (as if empty list)
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'b': {'Action': 'ADD', 'Value': [7]}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'c': {'Action': 'ADD', 'Value': ['a', 'b']}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [1, 2, 3, 4, 3, 5], 'b': [7], 'c': ['a', 'b']}
# Unlike sets which have a homogeneous element type, lists don't, and
# elements of any type can be appended to a list:
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'c': {'Action': 'ADD', 'Value': [3]}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == ['a', 'b', 3]
# ADD doesn't support any other type as the value parameter.
# In particular, it can't do things like append strings, or add items to
# a map, or add a single string value to a set.
with pytest.raises(ClientError, match='ValidationException.*type'):
test_table_s.put_item(Item={'p': p, 'a': 'dog'})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': 's'}})
with pytest.raises(ClientError, match='ValidationException.*type'):
test_table_s.put_item(Item={'p': p, 'a': {'x': 1}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': {'y': 2}}})
with pytest.raises(ClientError, match='ValidationException.*type'):
test_table_s.put_item(Item={'p': p, 'a': set(['dog'])})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': 'cat'}})
# If the entire item doesn't exist, ADD can create it just like we
# tested above that it can create an attribute.
for value in [3, set([1, 2]), set(['a', 'b']), [1, 2]]:
test_table_s.delete_item(Key={'p': p})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Action': 'ADD', 'Value': value}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': value}
# DynamoDB Does not allow empty sets.
# Trying to ask UpdateItem to PUT one of these in an attribute should be
# forbidden. Empty lists and maps *are* allowed.
def test_update_item_empty_attribute(test_table_s):
p = random_string()
# Empty sets are *not* allowed
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'c': {'Action': 'PUT', 'Value': set([])}})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# But empty lists, maps, strings and binary blobs *are* allowed:
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'d': {'Action': 'PUT', 'Value': []}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'e': {'Action': 'PUT', 'Value': {}}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'f': {'Action': 'PUT', 'Value': ''}})
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'g': {'Action': 'PUT', 'Value': bytearray('', 'utf-8')}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'd': [], 'e': {}, 'f': '', 'g': bytearray('', 'utf-8')}
# Test that empty strings are not accepted for keys
def test_update_item_empty_key(test_table_s, test_table_b, test_table_ss, test_table_sb):
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.update_item(Key={'p': ''}, AttributeUpdates={'v': {'Action': 'PUT', 'Value': 'abc'}})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_b.update_item(Key={'p': bytearray('', 'utf-8')}, AttributeUpdates={'v': {'Action': 'PUT', 'Value': 'abc'}})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_ss.update_item(Key={'p': 'abc', 'c': ''}, AttributeUpdates={'v': {'Action': 'PUT', 'Value': 'abc'}})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_sb.update_item(Key={'p': 'abc', 'c': bytearray('', 'utf-8')}, AttributeUpdates={'v': {'Action': 'PUT', 'Value': 'abc'}})
# Same as the above test (that we cannot create empty sets), but using PutItem
def test_put_item_empty_attribute(test_table_s):
p = random_string()
# Empty sets are *not* allowed
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.put_item(Item={'p': p, 'a': set([])})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# But empty lists, maps, strings and binary blobs *are* allowed:
test_table_s.put_item(Item={'p': p, 'a': [], 'b': {}, 'c': '', 'd': bytearray('', 'utf-8')})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [], 'b': {}, 'c': '', 'd': bytearray('', 'utf-8')}
# Test that empty strings are not accepted for keys
def test_put_item_empty_key(test_table_s, test_table_b, test_table_ss, test_table_sb):
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.put_item(Item={'p': '', 'v': 'something'})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_b.put_item(Item={'p': bytearray('', 'utf-8'), 'v': 'something'})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_ss.put_item(Item={'p': 'abc', 'c': '', 'v': 'something'})
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_sb.put_item(Item={'p': 'abc', 'c': bytearray('', 'utf-8'), 'v': 'something'})
# In many other tests, we tested that ExpressionAttributeNames/Values
# entries which aren't used in an the different kinds of expressions, are
# detected and cause an error. Here we verify that also if there is no
# expression at all, ExpressionAttributeNames/Values must not be present.
def test_unused_entries_no_expression(test_table_s):
p = random_string()
# PutItem:
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeNames'):
test_table_s.put_item(Item={'p': p, 'a': 'dog'},
ExpressionAttributeNames={'#name1': 'x'})
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeValues'):
test_table_s.put_item(Item={'p': p, 'a': 'dog'},
ExpressionAttributeValues={':val1': 1})
# DeleteItem:
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeNames'):
test_table_s.delete_item(Key={'p': p},
ExpressionAttributeNames={'#name1': 'x'})
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeValues'):
test_table_s.delete_item(Key={'p': p},
ExpressionAttributeValues={':val1': 1})
# UpdateItem:
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeNames'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 'dog', 'Action': 'PUT'}},
ExpressionAttributeNames={'#name1': 'x'})
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeValues'):
test_table_s.update_item(Key={'p': p},
AttributeUpdates={'a': {'Value': 'dog', 'Action': 'PUT'}},
ExpressionAttributeValues={':val1': 1})
# GetItem. We can't test ExpressionAttributeValues with boto3 (which
# doesn't allow this parameter to get_item().
with pytest.raises(ClientError, match='ValidationException.*ExpressionAttributeNames'):
test_table_s.get_item(Key={'p': p},
ExpressionAttributeNames={'#name1': 'x'})

View File

@@ -26,22 +26,25 @@ import time
from botocore.exceptions import ClientError, ParamValidationError
from util import create_test_table, random_string, full_scan, full_query, multiset, list_tables
# LSIs support strongly-consistent reads, so the following functions do not
# need to retry like we did in test_gsi.py for GSIs:
# Currently, Alternator's LSIs only support eventually consistent reads, so tests
# that involve writing to a table and then expect to read something from it cannot
# be guaranteed to succeed without retrying the read. The following utility
# functions make it easy to write such tests.
def assert_index_query(table, index_name, expected_items, **kwargs):
assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
def assert_index_scan(table, index_name, expected_items, **kwargs):
assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
# A version doing retries instead of ConsistentRead, to be used just for the
# one test below which has both GSI and LSI:
def retrying_assert_index_query(table, index_name, expected_items, **kwargs):
for i in range(3):
if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, ConsistentRead=False, **kwargs)):
if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
return
print('retrying_assert_index_query retrying')
print('assert_index_query retrying')
time.sleep(1)
assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, ConsistentRead=False, **kwargs))
assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
def assert_index_scan(table, index_name, expected_items, **kwargs):
for i in range(3):
if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
return
print('assert_index_scan retrying')
time.sleep(1)
assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
# Although quite silly, it is actually allowed to create an index which is
# identical to the base table.
@@ -63,7 +66,7 @@ def test_lsi_identical(dynamodb):
# results (in different order).
assert multiset(items) == multiset(full_scan(table))
assert_index_scan(table, 'hello', items)
# We can't scan a non-existent index
# We can't scan a non-existant index
with pytest.raises(ClientError, match='ValidationException'):
full_scan(table, IndexName='wrong')
table.delete()
@@ -125,9 +128,8 @@ def test_lsi_wrong(dynamodb):
])
table.delete()
# A simple scenario for LSI. Base table has a partition key and a sort key,
# index has the same partition key key but a different sort key - one of
# the non-key attributes from the base table.
# A simple scenario for LSI. Base table has just hash key, Index has an
# additional sort key - one of the non-key attributes from the base table.
@pytest.fixture(scope="session")
def test_table_lsi_1(dynamodb):
table = create_test_table(dynamodb,
@@ -213,12 +215,6 @@ def test_lsi_4(test_table_lsi_4):
KeyConditions={'p': {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'},
column: {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'}})
# Test that setting an indexed string column to an empty string is illegal,
# since keys cannot contain empty strings
def test_lsi_empty_value(test_table_lsi_1):
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_lsi_1.put_item(Item={'p': random_string(), 'c': random_string(), 'b': ''})
def test_lsi_describe(test_table_lsi_4):
desc = test_table_lsi_4.meta.client.describe_table(TableName=test_table_lsi_4.name)
assert 'Table' in desc
@@ -306,11 +302,13 @@ def test_lsi_consistent_read(test_table_lsi_1):
expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1]
assert_index_query(test_table_lsi_1, 'hello', expected_items,
KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}})
'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}},
ConsistentRead=True)
expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2]
assert_index_query(test_table_lsi_1, 'hello', expected_items,
KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}})
'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
ConsistentRead=True)
# A table with both gsi and lsi present
@pytest.fixture(scope="session")
@@ -362,36 +360,6 @@ def test_lsi_and_gsi(test_table_lsi_gsi):
for index in ['hello_g1', 'hello_l1']:
expected_items = [i for i in items if i['p'] == p1 and i['x1'] == x1]
retrying_assert_index_query(test_table_lsi_gsi, index, expected_items,
assert_index_query(test_table_lsi_gsi, index, expected_items,
KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
'x1': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
# This test is a version of test_filter_expression_and_projection_expression
# from test_filter_expression, which involves a Query which projects only
# one column but filters on another one, and the point is to verify that
# the implementation got also the filtered column (for the filtering to work)
# but did not return it with the results. This version does the same, except
# that either the filtered column, or the projected column, is an LSI key.
# In our implementation, LSI keys are implemented differently from ordinary
# attributes - they are real Scylla columns and not just items in the
# ":attrs" map - so this test checks that our implementation of the filtering
# and projection (and their combination) did not mess up this special case.
# This test reproduces issue #6951.
def test_lsi_filter_expression_and_projection_expression(test_table_lsi_1):
p = random_string()
test_table_lsi_1.put_item(Item={'p': p, 'c': 'hi', 'b': 'dog', 'y': 'cat'})
test_table_lsi_1.put_item(Item={'p': p, 'c': 'yo', 'b': 'mouse', 'y': 'horse'})
# Case 1: b (the LSI key) is in filter but not in projection:
got_items = full_query(test_table_lsi_1,
KeyConditionExpression='p=:p',
FilterExpression='b=:b',
ProjectionExpression='y',
ExpressionAttributeValues={':p': p, ':b': 'mouse'})
assert(got_items == [{'y': 'horse'}])
# Case 2: b (the LSI key) is in the projection, but not the filter:
got_items = full_query(test_table_lsi_1,
KeyConditionExpression='p=:p',
FilterExpression='y=:y',
ProjectionExpression='b',
ExpressionAttributeValues={':p': p, ':y': 'cat'})
assert(got_items == [{'b': 'dog'}])

View File

@@ -134,10 +134,10 @@ def test_projection_expression_path(test_table_s):
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0]')['Item'] == {'a': {'b': [2]}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2]')['Item'] == {'a': {'b': [{'x': 'hi', 'y': 'yo'}]}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2].y')['Item'] == {'a': {'b': [{'y': 'yo'}]}}
# Trying to read any sort of non-existent attribute returns an empty item.
# Trying to read any sort of non-existant attribute returns an empty item.
# This includes a non-existing top-level attribute, an attempt to read
# beyond the end of an array or a non-existent member of a dictionary, as
# well as paths which begin with a non-existent prefix.
# beyond the end of an array or a non-existant member of a dictionary, as
# well as paths which begin with a non-existant prefix.
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='x')['Item'] == {}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[3]')['Item'] == {}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.x')['Item'] == {}
@@ -147,7 +147,6 @@ def test_projection_expression_path(test_table_s):
# structured the same was as in the original item:
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.b[1]')['Item'] == {'a': {'b': [2, 4]}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.c')['Item'] == {'a': {'b': [2], 'c': 5}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.c,b')['Item'] == {'a': {'c': 5}, 'b': 'hello'}
# It is not allowed to read the same path multiple times. The error from
# DynamoDB looks like: "Invalid ProjectionExpression: Two document paths
# overlap with each other; must remove or rewrite one of these paths;
@@ -160,59 +159,6 @@ def test_projection_expression_path(test_table_s):
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,a.b[0]')['Item']
# Above in test_projection_expression_toplevel_syntax() we tested how
# name references (#name) work in top-level attributes. In the following
# two tests we test how they work in more elaborate paths:
# 1. Multiple path components can make multiple references, e.g., "#a.#b"
# 2. Conversely, a single reference, e.g., "#a", is always a single path
# component. Even if "#a" is "a.b", this refers to the literal attribute
# "a.b" - with a dot in its name - and not to the b element in a.
@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
def test_projection_expression_path_references(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'a': {'b': 1, 'c': 2}, 'b': 'hi'})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b')['Item'] == {'a': {'b': 1}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#n1.b', ExpressionAttributeNames={'#n1': 'a'})['Item'] == {'a': {'b': 1}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.#n2', ExpressionAttributeNames={'#n2': 'b'})['Item'] == {'a': {'b': 1}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#n1.#n2', ExpressionAttributeNames={'#n1': 'a', '#n2': 'b'})['Item'] == {'a': {'b': 1}}
# Missing or unused names in ExpressionAttributeNames are errors:
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.#n2', ExpressionAttributeNames={'#wrong': 'b'})
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.#n2', ExpressionAttributeNames={'#n2': 'b', '#unused': 'x'})
@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
def test_projection_expression_path_dot(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'a.b': 'hi', 'a': {'b': 'yo'}})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b')['Item'] == {'a': {'b': 'yo'}}
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#name': 'a.b'})['Item'] == {'a.b': 'hi'}
# DynamoDB does not allow "overlapping" paths to be listed in
# ProjectionExpression. This includes both identical paths, and paths where
# one is a sub-path of the other - e.g. "a.b" and "a.b.c". As we already saw
# above, paths with just a common *prefix* - e.g., "a.b, a.c" - are fine.
@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
def test_projection_expression_path_overlap(test_table_s):
# The overlap is tested symbolically, on the given paths, without any
# relation to what the item contains, or whether it even exists. So we
# don't even need to create an item for this test. We still need a
# key for the GetItem call :-)
p = random_string()
for expr in ['a, a',
'a.b, a.b',
'a[1], a[1]',
'a, a.b',
'a.b, a',
'a.b, a.b[2]',
'a.b, a.b.c',
'a, a.b[2].c',
]:
with pytest.raises(ClientError, match='ValidationException.* overlap'):
test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression=expr)
# Above we nested paths in ProjectionExpression, but just for the GetItem
# request. Let's verify they also work in Query and Scan requests:
@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
def test_query_projection_expression_path(test_table):
p = random_string()
@@ -239,22 +185,6 @@ def test_scan_projection_expression_path(test_table):
expected_items = [{'p': p, 'a': {'x': x['a']['x']}} for x in items]
assert multiset(expected_items) == multiset(got_items)
# BatchGetItem also supports ProjectionExpression, let's test that it
# applies to all items, and that it correctly suports document paths as well.
@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
def test_batch_get_item_projection_expression_path(test_table_s):
items = [{'p': random_string(), 'a': {'b': random_string()}, 'c': random_string()} for i in range(3)]
with test_table_s.batch_writer() as batch:
for item in items:
batch.put_item(item)
got_items = test_table_s.meta.client.batch_get_item(
RequestItems = {test_table_s.name: {
'Keys': [{'p': item['p']} for item in items],
'ProjectionExpression': 'a.b',
'ConsistentRead': True}})['Responses'][test_table_s.name]
expected_items = [{'a': {'b': item['a']['b']}} for item in items]
assert multiset(got_items) == multiset(expected_items)
# It is not allowed to use both ProjectionExpression and its older cousin,
# AttributesToGet, together. If trying to do this, DynamoDB produces an error
# like "Can not use both expression and non-expression parameters in the same
@@ -269,19 +199,3 @@ def test_projection_expression_and_attributes_to_get(test_table_s):
full_scan(test_table_s, ProjectionExpression='a', AttributesToGet=['a'])
with pytest.raises(ClientError, match='ValidationException.*both'):
full_query(test_table_s, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression='a', AttributesToGet=['a'])
# above in test_projection_expression_toplevel_syntax among other things
# we noted how spurious entries in ExpressionAttributeNames, not needed
# the the ProjectionExpression, cause an error. Sometimes we have two
# expressions in the same request, for example, both a ProjectionExpression
# and a KeyConditionExpression. It's only an error if a name is not
# needed by both of these expressions
def test_projection_expression_and_key_condition_expression(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
got_items = full_query(test_table_s,
KeyConditionExpression='#name1 = :val1',
ProjectionExpression='#name2',
ExpressionAttributeNames={'#name1': 'p', '#name2': 'a'},
ExpressionAttributeValues={':val1': p});
assert got_items == [{'a': 'hello'}]

View File

@@ -17,11 +17,6 @@
# along with Scylla. If not, see <http://www.gnu.org/licenses/>.
# Tests for the Query operation
# Some of the Query features are tested in separate files:
# * test_key_conditions.py: the KeyConditions paramter.
# * test_key_condition_expression.py: the KeyConditionExpression parameter.
# * test_filter_expression.py: the FilterExpression parameter.
# * test_query_filter.py: the QueryFilter parameter.
import random
import pytest
@@ -30,13 +25,126 @@ from decimal import Decimal
from util import random_string, random_bytes, full_query, multiset
from boto3.dynamodb.conditions import Key, Attr
def test_query_nonexistent_table(dynamodb):
client = dynamodb.meta.client
with pytest.raises(ClientError, match="ResourceNotFoundException"):
client.query(TableName="i_do_not_exist", KeyConditions={
# Test that scanning works fine with in-stock paginator
def test_query_basic_restrictions(dynamodb, filled_test_table):
test_table, items = filled_test_table
paginator = dynamodb.meta.client.get_paginator('query')
# EQ
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long']) == multiset(got_items)
# LT
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['12'], 'ComparisonOperator': 'LT'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
# LE
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'LE'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] <= '14']) == multiset(got_items)
# GT
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['15'], 'ComparisonOperator': 'GT'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] > '15']) == multiset(got_items)
# GE
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'GE'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '14']) == multiset(got_items)
# BETWEEN
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['155', '164'], 'ComparisonOperator': 'BETWEEN'}
}):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '155' and item['c'] <= '164']) == multiset(got_items)
# BEGINS_WITH
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': ['11'], 'ComparisonOperator': 'BEGINS_WITH'}
})
}):
print([item for item in items if item['p'] == 'long' and item['c'].startswith('11')])
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'].startswith('11')]) == multiset(got_items)
# Test that KeyConditionExpression parameter is supported
@pytest.mark.xfail(reason="KeyConditionExpression not supported yet")
def test_query_key_condition_expression(dynamodb, filled_test_table):
test_table, items = filled_test_table
paginator = dynamodb.meta.client.get_paginator('query')
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditionExpression=Key("p").eq("long") & Key("c").lt("12")):
got_items += page['Items']
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
def test_begins_with(dynamodb, test_table):
paginator = dynamodb.meta.client.get_paginator('query')
items = [{'p': 'unorthodox_chars', 'c': sort_key, 'str': 'a'} for sort_key in [u'ÿÿÿ', u'cÿbÿ', u'cÿbÿÿabg'] ]
with test_table.batch_writer() as batch:
for item in items:
batch.put_item(item)
# TODO(sarna): Once bytes type is supported, /xFF character should be tested
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': [u'ÿÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
}):
got_items += page['Items']
print(got_items)
assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'ÿÿ')])
got_items = []
for page in paginator.paginate(TableName=test_table.name, KeyConditions={
'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': [u'cÿbÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
}):
got_items += page['Items']
print(got_items)
assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'cÿbÿ')])
def test_begins_with_wrong_type(dynamodb, test_table_sn):
paginator = dynamodb.meta.client.get_paginator('query')
with pytest.raises(ClientError, match='ValidationException'):
for page in paginator.paginate(TableName=test_table_sn.name, KeyConditions={
'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
'c' : {'AttributeValueList': [17], 'ComparisonOperator': 'BEGINS_WITH'}
}):
pass
# Items returned by Query should be sorted by the sort key. The following
# tests verify that this is indeed the case, for the three allowed key types:
@@ -107,8 +215,6 @@ def test_query_sort_order_number(test_table_sn):
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers
# Note: this is a very partial check for the QueryFilter feature. See
# test_query_filter.py for much more exhaustive tests for this feature.
def test_query_filtering_attributes_equality(filled_test_table):
test_table, items = filled_test_table
@@ -138,6 +244,7 @@ def test_query_filtering_attributes_equality(filled_test_table):
assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
# Test that FilterExpression works as expected
@pytest.mark.xfail(reason="FilterExpression not supported yet")
def test_query_filter_expression(filled_test_table):
test_table, items = filled_test_table
@@ -149,6 +256,33 @@ def test_query_filter_expression(filled_test_table):
print(got_items)
assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
# QueryFilter can only contain non-key attributes in order to be compatible
def test_query_filtering_key_equality(filled_test_table):
test_table, items = filled_test_table
with pytest.raises(ClientError, match='ValidationException'):
query_filter = {
"c" : {
"AttributeValueList" : [ "5" ],
"ComparisonOperator": "EQ"
}
}
got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
print(got_items)
with pytest.raises(ClientError, match='ValidationException'):
query_filter = {
"attribute" : {
"AttributeValueList" : [ "x" ],
"ComparisonOperator": "EQ"
},
"p" : {
"AttributeValueList" : [ "5" ],
"ComparisonOperator": "EQ"
}
}
got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
print(got_items)
# Test Query with the AttributesToGet parameter. Result should include the
# selected attributes only - if one wants the key attributes as well, one
@@ -238,14 +372,14 @@ def test_query_select(test_table_sn):
batch.put_item(item)
# Verify that we get back the numbers in their sorted order. By default,
# query returns all attributes:
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})['Items']
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers
got_x_attributes = [x['x'] for x in got_items]
assert got_x_attributes == numbers
# Select=ALL_ATTRIBUTES does exactly the same as the default - return
# all attributes:
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='ALL_ATTRIBUTES')['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='ALL_ATTRIBUTES')['Items']
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers
got_x_attributes = [x['x'] for x in got_items]
@@ -253,28 +387,28 @@ def test_query_select(test_table_sn):
# Select=ALL_PROJECTED_ATTRIBUTES is not allowed on a base table (it
# is just for indexes, when IndexName is specified)
with pytest.raises(ClientError, match='ValidationException'):
test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='ALL_PROJECTED_ATTRIBUTES')
test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='ALL_PROJECTED_ATTRIBUTES')
# Select=SPECIFIC_ATTRIBUTES requires that either a AttributesToGet
# or ProjectionExpression appears, but then really does nothing:
with pytest.raises(ClientError, match='ValidationException'):
test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES')
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES', AttributesToGet=['x'])['Items']
test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES')
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES', AttributesToGet=['x'])['Items']
expected_items = [{'x': i} for i in numbers]
assert got_items == expected_items
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES', ProjectionExpression='x')['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='SPECIFIC_ATTRIBUTES', ProjectionExpression='x')['Items']
assert got_items == expected_items
# Select=COUNT just returns a count - not any items
got = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='COUNT')
got = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='COUNT')
assert got['Count'] == len(numbers)
assert not 'Items' in got
# Check again that we also get a count - not just with Select=COUNT,
# but without Select=COUNT we also get the items:
got = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
got = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
assert got['Count'] == len(numbers)
assert 'Items' in got
# Select with some unknown string generates a validation exception:
with pytest.raises(ClientError, match='ValidationException'):
test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='UNKNOWN')
test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Select='UNKNOWN')
# Test that the "Limit" parameter can be used to return only some of the
# items in a single partition. The items returned are the first in the
@@ -290,20 +424,20 @@ def test_query_limit(test_table_sn):
# Verify that we get back the numbers in their sorted order.
# First, no Limit so we should get all numbers (we have few of them, so
# it all fits in the default 1MB limitation)
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})['Items']
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers
# Now try a few different Limit values, and verify that the query
# returns exactly the first Limit sorted numbers.
for limit in [1, 2, 3, 7, 10, 17, 100, 10000]:
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit)['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit)['Items']
assert len(got_items) == min(limit, len(numbers))
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers[0:limit]
# Unfortunately, the boto3 library forbids a Limit of 0 on its own,
# before even sending a request, so we can't test how the server responds.
with pytest.raises(ParamValidationError):
test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=0)
test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=0)
# In test_query_limit we tested just that Limit allows to stop the result
# after right right number of items. Here we test that such a stopped result
@@ -328,6 +462,7 @@ def test_query_limit_paging(test_table_sn):
# return items sorted in reverse order. Combining this with Limit can
# be used to return the last items instead of the first items of the
# partition.
@pytest.mark.xfail(reason="ScanIndexForward not supported yet")
def test_query_reverse(test_table_sn):
numbers = [Decimal(i) for i in range(20)]
# Insert these numbers, in random order, into one partition:
@@ -341,27 +476,28 @@ def test_query_reverse(test_table_sn):
# First, no Limit so we should get all numbers (we have few of them, so
# it all fits in the default 1MB limitation)
reversed_numbers = list(reversed(numbers))
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ScanIndexForward=True)['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ScanIndexForward=True)['Items']
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ScanIndexForward=False)['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ScanIndexForward=False)['Items']
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == reversed_numbers
# Now try a few different Limit values, and verify that the query
# returns exactly the first Limit sorted numbers - in regular or
# reverse order, depending on ScanIndexForward.
for limit in [1, 2, 3, 7, 10, 17, 100, 10000]:
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit, ScanIndexForward=True)['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit, ScanIndexForward=True)['Items']
assert len(got_items) == min(limit, len(numbers))
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == numbers[0:limit]
got_items = test_table_sn.query(ConsistentRead=True, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit, ScanIndexForward=False)['Items']
got_items = test_table_sn.query(KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, Limit=limit, ScanIndexForward=False)['Items']
assert len(got_items) == min(limit, len(numbers))
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == reversed_numbers[0:limit]
# Test that paging also works properly with reverse order
# (ScanIndexForward=false), i.e., reverse-order queries can be resumed
@pytest.mark.xfail(reason="ScanIndexForward not supported yet")
def test_query_reverse_paging(test_table_sn):
numbers = [Decimal(i) for i in range(20)]
# Insert these numbers, in random order, into one partition:
@@ -378,11 +514,3 @@ def test_query_reverse_paging(test_table_sn):
got_items = full_query(test_table_sn, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ScanIndexForward=False, Limit=limit)
got_sort_keys = [x['c'] for x in got_items]
assert got_sort_keys == reversed_numbers
# A query without a KeyConditions or KeyConditionExpress is, or an empty
# one, is obviously not allowed:
def test_query_missing_key(test_table):
with pytest.raises(ClientError, match='ValidationException'):
full_query(test_table, KeyConditions={})
with pytest.raises(ClientError, match='ValidationException'):
full_query(test_table)

View File

@@ -58,6 +58,7 @@ def test_trivial_returnvalues(test_table_s):
# Test the ReturnValues parameter on a PutItem operation. Only two settings
# are supported for this parameter for this operation: NONE (the default)
# and ALL_OLD.
@pytest.mark.xfail(reason="ReturnValues not supported")
def test_put_item_returnvalues(test_table_s):
# By default, the previous value of an item is not returned:
p = random_string()
@@ -75,11 +76,6 @@ def test_put_item_returnvalues(test_table_s):
test_table_s.put_item(Item={'p': p, 'a': 'hi'})
ret=test_table_s.put_item(Item={'p': p, 'a': 'hello'}, ReturnValues='ALL_OLD')
assert ret['Attributes'] == {'p': p, 'a': 'hi'}
# If the item does not previously exist, "Attributes" is not returned
# at all:
p = random_string()
ret=test_table_s.put_item(Item={'p': p, 'a': 'hello'}, ReturnValues='ALL_OLD')
assert not 'Attributes' in ret
# Other ReturnValue options - UPDATED_OLD, ALL_NEW, UPDATED_NEW,
# are supported by other operations but not by PutItem:
with pytest.raises(ClientError, match='ValidationException'):
@@ -99,6 +95,7 @@ def test_put_item_returnvalues(test_table_s):
# Test the ReturnValues parameter on a DeleteItem operation. Only two settings
# are supported for this parameter for this operation: NONE (the default)
# and ALL_OLD.
@pytest.mark.xfail(reason="ReturnValues not supported")
def test_delete_item_returnvalues(test_table_s):
# By default, the previous value of an item is not returned:
p = random_string()
@@ -116,11 +113,6 @@ def test_delete_item_returnvalues(test_table_s):
test_table_s.put_item(Item={'p': p, 'a': 'hi'})
ret=test_table_s.delete_item(Key={'p': p}, ReturnValues='ALL_OLD')
assert ret['Attributes'] == {'p': p, 'a': 'hi'}
# If the item does not previously exist, "Attributes" is not returned
# at all:
p = random_string()
ret=test_table_s.delete_item(Key={'p': p}, ReturnValues='ALL_OLD')
assert not 'Attributes' in ret
# Other ReturnValue options - UPDATED_OLD, ALL_NEW, UPDATED_NEW,
# are supported by other operations but not by PutItem:
with pytest.raises(ClientError, match='ValidationException'):
@@ -140,10 +132,8 @@ def test_delete_item_returnvalues(test_table_s):
# Test the ReturnValues parameter on a UpdateItem operation. All five
# settings are supported for this parameter for this operation: NONE
# (the default), ALL_OLD, UPDATED_OLD, ALL_NEW and UPDATED_NEW.
# We test them in separate tests to allow for this feature to be
# implemented incrementally.
def test_update_item_returnvalues_none(test_table_s):
@pytest.mark.xfail(reason="ReturnValues not supported")
def test_update_item_returnvalues(test_table_s):
# By default, the previous value of an item is not returned:
p = random_string()
test_table_s.put_item(Item={'p': p, 'a': 'hi', 'b': 'dog'})
@@ -160,20 +150,6 @@ def test_update_item_returnvalues_none(test_table_s):
ExpressionAttributeValues={':val': 'cat'})
assert not 'Attributes' in ret
# The ReturnValues value is case sensitive, so while "NONE" is supported
# (and tested above), "none" isn't:
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p}, ReturnValues='none',
UpdateExpression='SET a = :val',
ExpressionAttributeValues={':val': 1})
# A non-supported setting "DOG" also returns in error:
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p}, ReturnValues='DOG',
UpdateExpression='SET a = :val',
ExpressionAttributeValues={':val': 1})
def test_update_item_returnvalues_all_old(test_table_s):
# With ReturnValues=ALL_OLD, the entire old value of the item (even
# attributes we did not modify) is returned in an "Attributes" attribute:
p = random_string()
@@ -183,15 +159,6 @@ def test_update_item_returnvalues_all_old(test_table_s):
ExpressionAttributeValues={':val': 'cat'})
assert ret['Attributes'] == {'p': p, 'a': 'hi', 'b': 'dog'}
# If the item does not previously exist, "Attributes" is not returned
# at all:
p = random_string()
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_OLD',
UpdateExpression='SET b = :val',
ExpressionAttributeValues={':val': 'cat'})
assert not 'Attributes' in ret
def test_update_item_returnvalues_updated_old(test_table_s):
# With ReturnValues=UPDATED_OLD, only the overwritten attributes of the
# old item are returned in an "Attributes" attribute:
p = random_string()
@@ -200,7 +167,6 @@ def test_update_item_returnvalues_updated_old(test_table_s):
UpdateExpression='SET b = :val, c = :val2',
ExpressionAttributeValues={':val': 'cat', ':val2': 'hello'})
assert ret['Attributes'] == {'b': 'dog'}
# Even if an update overwrites an attribute by the same value again,
# this is considered an update, and the old value (identical to the
# new one) is returned:
@@ -208,40 +174,11 @@ def test_update_item_returnvalues_updated_old(test_table_s):
UpdateExpression='SET b = :val',
ExpressionAttributeValues={':val': 'cat'})
assert ret['Attributes'] == {'b': 'cat'}
# Deleting an attribute also counts as overwriting it, of course:
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='REMOVE b')
assert ret['Attributes'] == {'b': 'cat'}
# If we write to an attribute that didn't exist before, we do not
# get Attributes at all:
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET b = :val',
ExpressionAttributeValues={':val': 'cat'})
assert not 'Attributes' in ret
# However, if we write to two attributes, one which previously existed
# and one didn't, we get back only the one which previously existed:
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET b = :val, d = :val2',
ExpressionAttributeValues={':val': 'dog', ':val2': 'lion'})
assert ret['Attributes'] == {'b': 'cat'}
# Of course if we write to two attributes which previously existed,
# we get both of them back
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET b = :val, d = :val2',
ExpressionAttributeValues={':val': 'cat', ':val2': 'tiger'})
assert ret['Attributes'] == {'b': 'dog', 'd': 'lion'}
# If we write absolutely nothing (the only way to do this is with the
# old AttributeUpdates syntax), we don't get Attributes back.
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
AttributeUpdates={})
assert not 'Attributes' in ret
def test_update_item_returnvalues_all_new(test_table_s):
# With ReturnValues=ALL_NEW, the entire new value of the item (including
# old attributes we did not modify) is returned:
p = random_string()
@@ -251,67 +188,21 @@ def test_update_item_returnvalues_all_new(test_table_s):
ExpressionAttributeValues={':val': 'cat'})
assert ret['Attributes'] == {'p': p, 'a': 'hi', 'b': 'cat'}
# Verify that if a column is deleted, it is *not* returned:
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='REMOVE b')
assert ret['Attributes'] == {'p': p, 'a': 'hi'}
# If the item did not previously exist, that's still fine, we get the
# new value of the item:
p = random_string()
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='SET b = :val',
ExpressionAttributeValues={':val': 'cat'})
assert ret['Attributes'] == {'p': p, 'b': 'cat'}
# A more interesting question is what happens if the item did not
# previously exist, and all the update does is *delete* an attribute,
# which never existed. In this case, the item is not created (see also
# test_update_item_non_existent()), and "Attributes" is not returned,
p = random_string()
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='REMOVE b')
assert not 'Attributes' in ret
ret=test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
assert not 'Item' in ret
# If we write absolutely nothing (the only way to do this is with the
# old AttributeUpdates syntax), we get an empty item (just the key)
# if it didn't yet exist (and now it does), or the old item if it did.
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
AttributeUpdates={})
assert ret['Attributes'] == {'p': p}
test_table_s.put_item(Item={'p': p, 'a': 'hi'})
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
AttributeUpdates={})
assert ret['Attributes'] == {'p': p, 'a': 'hi'}
def test_update_item_returnvalues_updated_new(test_table_s):
# With ReturnValues=UPDATED_NEW, only the new value of the updated
# attributes are returned. Note that "updated attributes" means
# the newly set attributes - it doesn't require that these attributes
# have any previous values.
# have any previous values
p = random_string()
test_table_s.put_item(Item={'p': p, 'a': 'hi', 'b': 'dog'})
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET b = :val, c = :val2',
ExpressionAttributeValues={':val': 'cat', ':val2': 'hello'})
assert ret['Attributes'] == {'b': 'cat', 'c': 'hello'}
# Deleting an attribute also counts as overwriting it, but the deleted
# Deleting an attribute also counts as overwriting it, but the delete
# column is not returned in the response - so it's empty in this case.
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='REMOVE b')
assert not 'Attributes' in ret
# Verify If we write to multiple attributes, we get them all back,
# regardless of whether they previously existed or not (and again,
# deleted columns aren't returned):
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET a = :val, b = :val2 REMOVE c',
ExpressionAttributeValues={':val': 'dog', ':val2': 'tiger'})
assert ret['Attributes'] == {'a': 'dog', 'b': 'tiger'}
# In the above examples, UPDATED_NEW is not useful because it just
# returns the new values we already know from the request... UPDATED_NEW
# becomes more useful in read-modify-write operations:
@@ -322,79 +213,14 @@ def test_update_item_returnvalues_updated_new(test_table_s):
ExpressionAttributeValues={':val': 1})
assert ret['Attributes'] == {'a': 2}
# UPDATED_NEW only returns non-key attributes. Even if the operation
# caused a new item to be created, the new key attributes aren't
# returned.
p = random_string()
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET a = :val',
ExpressionAttributeValues={':val': 1})
assert ret['Attributes'] == {'a': 1}
# If we write absolutely nothing (the only way to do this is with the
# old AttributeUpdates syntax), we don't get back any Attributes.
# Not even if the item didn't previously exist and this write caused
# it to be created.
p = random_string()
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
AttributeUpdates={})
assert not 'Attributes' in ret
test_table_s.put_item(Item={'p': p, 'a': 'hi'})
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
AttributeUpdates={})
assert not 'Attributes' in ret
# Test the ReturnValues from an UpdateItem directly modifying a *nested*
# attribute, in the relevant ReturnValue modes:
@pytest.mark.xfail(reason="nested updates not yet implemented")
def test_update_item_returnvalues_nested(test_table_s):
p = random_string()
test_table_s.put_item(Item={'p': p, 'a': {'b': 'dog', 'c': [1, 2, 3]}, 'd': 'cat'})
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_OLD',
UpdateExpression='SET a.b = :val',
ExpressionAttributeValues={':val': 'hi'})
assert ret['Attributes'] == {'p': p, 'a': {'b': 'dog', 'c': [1, 2, 3]}, 'd': 'cat'}
# UPDATED_OLD and UPDATED_NEW return *only* the nested attribute, not
# the entire top-level attribute. It still needs to return it nested
# within its the appropriate hierarchy, but not containing the entire
# top-level attribute.
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET a.b = :val',
ExpressionAttributeValues={':val': 'yo'})
assert ret['Attributes'] == {'a': {'b': 'hi'}}
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET a.c[1] = :val',
ExpressionAttributeValues={':val': 7})
assert ret['Attributes'] == {'a': {'c': [2]}}
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_OLD',
UpdateExpression='SET a.c[1] = :val, a.b = :val2',
ExpressionAttributeValues={':val': 8, ':val2': 'dog'})
assert ret['Attributes'] == {'a': {'b': 'yo', 'c': [7]}}
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET a.b = :val',
ExpressionAttributeValues={':val': 'hello'})
assert ret['Attributes'] == {'a': {'b': 'hello'}}
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET a.c[1] = :val',
ExpressionAttributeValues={':val': 4})
assert ret['Attributes'] == {'a': {'c': [4]}}
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='UPDATED_NEW',
UpdateExpression='SET a.c[1] = :val, a.b = :val2',
ExpressionAttributeValues={':val': 3, ':val2': 'dog'})
assert ret['Attributes'] == {'a': {'b': 'dog', 'c': [3]}}
# Although ALL_NEW mode returns the entire item and doesn't need to
# know how to project a nested attribute, we still need to check that
# it can return the post-update value of the attribute within the entire
# item.
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='SET a.b = :val',
ExpressionAttributeValues={':val': 'hi'})
assert ret['Attributes'] == {'p': p, 'a': {'b': 'hi', 'c': [1, 3, 3]}, 'd': 'cat' }
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='SET a.c[1] = :val',
ExpressionAttributeValues={':val': 4})
assert ret['Attributes'] == {'p': p, 'a': {'b': 'hi', 'c': [1, 4, 3]}, 'd': 'cat' }
ret=test_table_s.update_item(Key={'p': p}, ReturnValues='ALL_NEW',
UpdateExpression='SET a.c[1] = :val, a.b = :val2',
ExpressionAttributeValues={':val': 3, ':val2': 'dog'})
assert ret['Attributes'] == {'p': p, 'a': {'b': 'dog', 'c': [1, 3, 3]}, 'd': 'cat' }
# A non-supported setting "DOG" also returns in error:
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p}, ReturnValues='DOG',
UpdateExpression='SET a = a + :val',
ExpressionAttributeValues={':val': 1})
# The ReturnValues value is case sensitive, so while "NONE" is supported
# (and tested above), "none" isn't:
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p}, ReturnValues='none',
UpdateExpression='SET a = a + :val',
ExpressionAttributeValues={':val': 1})

View File

@@ -30,10 +30,10 @@ def test_scan_basic(filled_test_table):
got_items = []
while True:
if limit:
response = test_table.scan(Limit=limit, ConsistentRead=True, ExclusiveStartKey=pos) if pos else test_table.scan(Limit=limit, ConsistentRead=True)
response = test_table.scan(Limit=limit, ExclusiveStartKey=pos) if pos else test_table.scan(Limit=limit)
assert len(response['Items']) <= limit
else:
response = test_table.scan(ExclusiveStartKey=pos, ConsistentRead=True) if pos else test_table.scan(ConsistentRead=True)
response = test_table.scan(ExclusiveStartKey=pos) if pos else test_table.scan()
pos = response.get('LastEvaluatedKey', None)
got_items += response['Items']
if not pos:
@@ -42,11 +42,6 @@ def test_scan_basic(filled_test_table):
assert len(items) == len(got_items)
assert multiset(items) == multiset(got_items)
def test_scan_nonexistent_table(dynamodb):
client = dynamodb.meta.client
with pytest.raises(ClientError, match="ResourceNotFoundException"):
client.scan(TableName="i_do_not_exist")
def test_scan_with_paginator(dynamodb, filled_test_table):
test_table, items = filled_test_table
paginator = dynamodb.meta.client.get_paginator('scan')
@@ -128,6 +123,7 @@ def test_scan_with_attribute_equality_filtering(dynamodb, filled_test_table):
assert multiset(expected_items) == multiset(got_items)
# Test that FilterExpression works as expected
@pytest.mark.xfail(reason="FilterExpression not supported yet")
def test_scan_filter_expression(filled_test_table):
test_table, items = filled_test_table
@@ -243,6 +239,7 @@ def test_scan_select(filled_test_table):
# a scan into multiple parts, and that these parts are in fact disjoint,
# and their union is the entire contents of the table. We do not actually
# try to run these queries in *parallel* in this test.
@pytest.mark.xfail(reason="parallel scan not supported yet")
def test_scan_parallel(filled_test_table):
test_table, items = filled_test_table
for nsegments in [1, 2, 17]:
@@ -253,14 +250,3 @@ def test_scan_parallel(filled_test_table):
# The following comparison verifies that each of the expected item
# in items was returned in one - and just one - of the segments.
assert multiset(items) == multiset(got_items)
# Test correct handling of incorrect parallel scan parameters.
# Most of the corner cases (like TotalSegments=0) are validated
# by boto3 itself, but some checks can still be performed.
def test_scan_parallel_incorrect(filled_test_table):
test_table, items = filled_test_table
with pytest.raises(ClientError, match='ValidationException.*Segment'):
full_scan(test_table, TotalSegments=1000001, Segment=0)
for segment in [7, 9]:
with pytest.raises(ClientError, match='ValidationException.*Segment'):
full_scan(test_table, TotalSegments=5, Segment=segment)

View File

@@ -74,11 +74,6 @@ def create_and_delete_table(dynamodb, name, **kwargs):
def test_create_and_delete_table(dynamodb):
create_and_delete_table(dynamodb, 'alternator_test')
# Test that recreating a table right after deleting it works without issues
def test_recreate_table(dynamodb):
create_and_delete_table(dynamodb, 'alternator_recr_test')
create_and_delete_table(dynamodb, 'alternator_recr_test')
# DynamoDB documentation specifies that table names must be 3-255 characters,
# and match the regex [a-zA-Z0-9._-]+. Names not matching these rules should
# be rejected, and no table be created.
@@ -200,7 +195,7 @@ def test_create_table_invalid_schema(dynamodb):
# Test that trying to create a table that already exists fails in the
# appropriate way (ResourceInUseException)
def test_create_table_already_exists(dynamodb, test_table):
with pytest.raises(ClientError, match='ResourceInUseException.*Table.*already exists'):
with pytest.raises(ClientError, match='ResourceInUseException'):
create_table(dynamodb, test_table.name)
# Test that BillingMode error path works as expected - only the values
@@ -232,35 +227,6 @@ def test_create_table_billing_mode_errors(dynamodb, test_table):
KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }])
# Even before Alternator gains full support for the DynamoDB stream API
# and CreateTable's StreamSpecification option, we should support the
# options which mean it is turned *off*.
def test_table_streams_off(dynamodb):
# If StreamSpecification is given, but has StreamEnabled=false, it's as
# if StreamSpecification was missing. StreamViewType isn't needed.
table = create_test_table(dynamodb, StreamSpecification={'StreamEnabled': False},
KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }]);
table.delete();
# DynamoDB doesn't allow StreamSpecification to be empty map - if it
# exists, it must have a StreamEnabled
# Unfortunately, new versions of boto3 doesn't let us pass this...
#with pytest.raises(ClientError, match='ValidationException'):
# table = create_test_table(dynamodb, StreamSpecification={},
# KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
# AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }]);
# table.delete();
# Unfortunately, boto3 doesn't allow us to pass StreamSpecification=None.
# This is what we had in issue #5796.
def test_table_streams_on(dynamodb):
for type in [ 'OLD_IMAGE', 'NEW_IMAGE', 'KEYS_ONLY', 'NEW_AND_OLD_IMAGES']:
table = create_test_table(dynamodb,
StreamSpecification={'StreamEnabled': True, 'StreamViewType': type},
KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }]);
table.delete();
# Our first implementation had a special column name called "attrs" where
# we stored a map for all non-key columns. If the user tried to name one
# of the key columns with this same name, the result was a disaster - Scylla
@@ -308,17 +274,3 @@ def test_list_tables_wrong_limit(dynamodb):
# lower limit (min. 1) is imposed by boto3 library checks
with pytest.raises(ClientError, match='ValidationException'):
dynamodb.meta.client.list_tables(Limit=101)
# Even before Alternator gains support for configuring server-side encryption
# ("encryption at rest") with CreateTable's SSESpecification option, we should
# support the option "Enabled=false" which is the default, and means the server
# takes care of whatever server-side encryption is done, on its own.
# Reproduces issue #7031.
def test_table_sse_off(dynamodb):
# If StreamSpecification is given, but has StreamEnabled=false, it's as
# if StreamSpecification was missing, and fine. No other attribues are
# necessary.
table = create_test_table(dynamodb, SSESpecification = {'Enabled': False},
KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }]);
table.delete();

View File

@@ -21,6 +21,7 @@ import random
import string
import pytest
from botocore.exceptions import ClientError
from decimal import Decimal
from util import random_string
# The simplest test of using UpdateExpression to set a top-level attribute,
@@ -369,7 +370,7 @@ def test_update_expression_cannot_modify_key(test_table):
# Test that trying to start an expression with some nonsense like HELLO
# instead of SET, REMOVE, ADD or DELETE, fails.
def test_update_expression_non_existent_clause(test_table_s):
def test_update_expression_non_existant_clause(test_table_s):
p = random_string()
with pytest.raises(ClientError, match='ValidationException'):
test_table_s.update_item(Key={'p': p},
@@ -406,6 +407,21 @@ def test_update_expression_plus_basic(test_table_s):
UpdateExpression='SET b = :val1 + :val2',
ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['1', '2']})
# While most of the Alternator code just saves high-precision numbers
# unchanged, the "+" and "-" operations need to calculate with them, and
# we should check the calculation isn't done with some lower-precision
# representation, e.g., double
def test_update_expression_plus_precision(test_table_s):
p = random_string()
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET b = :val1 + :val2',
ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("10000000000000000000001")}
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET b = :val2 - :val1',
ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("9999999999999999999999")}
# Test support for "SET a = b + :val2" et al., i.e., a version of the
# above test_update_expression_plus_basic with read before write.
def test_update_expression_plus_rmw(test_table_s):
@@ -701,28 +717,10 @@ def test_update_expression_delete_sets(test_table_s):
UpdateExpression='DELETE a :val1',
ExpressionAttributeValues={':val1': set(['pig'])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog'])
# Deleting all the elements cannot leave an empty set (which isn't
# supported). Rather, it deletes the attribute altogether:
test_table_s.update_item(Key={'p': p},
UpdateExpression='DELETE a :val1',
ExpressionAttributeValues={':val1': set(['dog'])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hi'}
# Deleting elements from a non-existent attribute is allowed, and
# simply does nothing:
test_table_s.update_item(Key={'p': p},
UpdateExpression='DELETE a :val1',
ExpressionAttributeValues={':val1': set(['dog'])})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hi'}
# An empty set parameter is not allowed
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='DELETE a :val1',
ExpressionAttributeValues={':val1': set([])})
# The value to be deleted must be a set of the same type - it can't
# be a single element or anything else. If the value has the wrong type,
# we get an error like "Invalid UpdateExpression: Incorrect operand type
# for operator or function; operator: DELETE, operand type: STRING".
test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'mouse']), 'b': 'hi'})
with pytest.raises(ClientError, match='ValidationException.*type'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='DELETE a :val1',
@@ -854,24 +852,3 @@ def test_nested_attribute_update_bad_path_array(test_table_s):
with pytest.raises(ClientError, match='ValidationException.*path'):
test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[0] = :val1',
ExpressionAttributeValues={':val1': 7})
# DynamoDB Does not allow empty sets.
# Trying to ask UpdateItem to put one of these in an attribute should be
# forbidden. Empty lists and maps *are* allowed.
# Note that in test_item.py::test_update_item_empty_attribute we checked
# this with the AttributeUpdates syntax. Here we check the same with the
# UpdateExpression syntax.
def test_update_expression_empty_attribute(test_table_s):
p = random_string()
# Empty sets are *not* allowed
with pytest.raises(ClientError, match='ValidationException.*empty'):
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET a = :v',
ExpressionAttributeValues={':v': set()})
assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
# But empty lists, maps, strings and binary blobs *are* allowed:
test_table_s.update_item(Key={'p': p},
UpdateExpression='SET d = :v1, e = :v2, f = :v3, g = :v4',
ExpressionAttributeValues={':v1': [], ':v2': {}, ':v3': '', ':v4': b''})
assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'd': [], 'e': {}, 'f': '', 'g': b''}
#

View File

@@ -28,18 +28,14 @@ def random_string(length=10, chars=string.ascii_uppercase + string.digits):
def random_bytes(length=10):
return bytearray(random.getrandbits(8) for _ in range(length))
# Utility functions for scan and query into an array of items, reading
# the full (possibly requiring multiple requests to read successive pages).
# For convenience, ConsistentRead=True is used by default, as most tests
# need it to run correctly on a multi-node cluster. Callers who need to
# override it, can (this is necessary in GSI tests, where ConsistentRead=True
# is not supported).
def full_scan(table, ConsistentRead=True, **kwargs):
response = table.scan(ConsistentRead=ConsistentRead, **kwargs)
# Utility functions for scan and query into an array of items:
# TODO: add to full_scan and full_query by default ConsistentRead=True, as
# it's not useful for tests without it!
def full_scan(table, **kwargs):
response = table.scan(**kwargs)
items = response['Items']
while 'LastEvaluatedKey' in response:
response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'],
ConsistentRead=ConsistentRead, **kwargs)
response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
items.extend(response['Items'])
return items
@@ -47,8 +43,8 @@ def full_scan(table, ConsistentRead=True, **kwargs):
# Note that count isn't simply len(items) - the server returns them
# independently. e.g., with Select='COUNT' the items are not returned, but
# count is.
def full_scan_and_count(table, ConsistentRead=True, **kwargs):
response = table.scan(ConsistentRead=ConsistentRead, **kwargs)
def full_scan_and_count(table, **kwargs):
response = table.scan(**kwargs)
items = []
count = 0
if 'Items' in response:
@@ -56,8 +52,7 @@ def full_scan_and_count(table, ConsistentRead=True, **kwargs):
if 'Count' in response:
count = count + response['Count']
while 'LastEvaluatedKey' in response:
response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'],
ConsistentRead=ConsistentRead, **kwargs)
response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
if 'Items' in response:
items.extend(response['Items'])
if 'Count' in response:
@@ -65,45 +60,14 @@ def full_scan_and_count(table, ConsistentRead=True, **kwargs):
return (count, items)
# Utility function for fetching the entire results of a query into an array of items
def full_query(table, ConsistentRead=True, **kwargs):
response = table.query(ConsistentRead=ConsistentRead, **kwargs)
def full_query(table, **kwargs):
response = table.query(**kwargs)
items = response['Items']
while 'LastEvaluatedKey' in response:
response = table.query(ExclusiveStartKey=response['LastEvaluatedKey'],
ConsistentRead=ConsistentRead, **kwargs)
response = table.query(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
items.extend(response['Items'])
return items
# full_query_and_counts returns both items and counts (pre-filter and
# post-filter count) as returned by the server.
# Note that count isn't simply len(items) - the server returns them
# independently. e.g., with Select='COUNT' the items are not returned, but
# count is.
def full_query_and_counts(table, ConsistentRead=True, **kwargs):
response = table.query(ConsistentRead=ConsistentRead, **kwargs)
items = []
prefilter_count = 0
postfilter_count = 0
pages = 0
if 'Items' in response:
items.extend(response['Items'])
pages = pages + 1
if 'Count' in response:
postfilter_count = postfilter_count + response['Count']
if 'ScannedCount' in response:
prefilter_count = prefilter_count + response['ScannedCount']
while 'LastEvaluatedKey' in response:
response = table.query(ExclusiveStartKey=response['LastEvaluatedKey'],
ConsistentRead=ConsistentRead, **kwargs)
if 'Items' in response:
items.extend(response['Items'])
pages = pages + 1
if 'Count' in response:
postfilter_count = postfilter_count + response['Count']
if 'ScannedCount' in response:
prefilter_count = prefilter_count + response['ScannedCount']
return (prefilter_count, postfilter_count, pages, items)
# To compare two lists of items (each is a dict) without regard for order,
# "==" is not good enough because it will fail if the order is different.
# The following function, multiset() converts the list into a multiset
@@ -120,9 +84,8 @@ def freeze(item):
def multiset(items):
return collections.Counter([freeze(item) for item in items])
# NOTE: alternator_Test prefix contains a capital letter on purpose,
#in order to validate case sensitivity in alternator
test_table_prefix = 'alternator_Test_'
test_table_prefix = 'alternator_test_'
def test_table_name():
current_ms = int(round(time.time() * 1000))
# In the off chance that test_table_name() is called twice in the same millisecond...

View File

@@ -78,12 +78,12 @@ void check_expiry(std::string_view signature_date) {
std::string expiration_str = format_time_point(db_clock::now() - 15min);
std::string validity_str = format_time_point(db_clock::now() + 15min);
if (signature_date < expiration_str) {
throw api_error::invalid_signature(
throw api_error("InvalidSignatureException",
fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
signature_date, expiration_str));
}
if (signature_date > validity_str) {
throw api_error::invalid_signature(
throw api_error("InvalidSignatureException",
fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
signature_date, validity_str));
}
@@ -94,13 +94,13 @@ std::string get_signature(std::string_view access_key_id, std::string_view secre
std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
auto amz_date_it = signed_headers_map.find("x-amz-date");
if (amz_date_it == signed_headers_map.end()) {
throw api_error::invalid_signature("X-Amz-Date header is mandatory for signature verification");
throw api_error("InvalidSignatureException", "X-Amz-Date header is mandatory for signature verification");
}
std::string_view amz_date = amz_date_it->second;
check_expiry(amz_date);
std::string_view datestamp = amz_date.substr(0, 8);
if (datestamp != orig_datestamp) {
throw api_error::invalid_signature(
throw api_error("InvalidSignatureException",
format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
orig_datestamp, datestamp));
}
@@ -126,18 +126,19 @@ std::string get_signature(std::string_view access_key_id, std::string_view secre
future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
auth::meta::roles_table::qualified_name, auth::meta::roles_table::role_col_name);
auth::meta::roles_table::qualified_name(), auth::meta::roles_table::role_col_name);
auto cl = auth::password_authenticator::consistency_for_user(username);
return qp.execute_internal(query, cl, auth::internal_distributed_query_state(), {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
auto timeout = auth::internal_distributed_timeout_config();
return qp.process(query, cl, timeout, {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
auto res = f.get0();
auto salted_hash = std::optional<sstring>();
if (res->empty()) {
throw api_error::unrecognized_client(fmt::format("User not found: {}", username));
throw api_error("UnrecognizedClientException", fmt::format("User not found: {}", username));
}
salted_hash = res->one().get_opt<sstring>("salted_hash");
if (!salted_hash) {
throw api_error::unrecognized_client(fmt::format("No password found for user: {}", username));
throw api_error("UnrecognizedClientException", fmt::format("No password found for user: {}", username));
}
return make_ready_future<std::string>(*salted_hash);
});

View File

@@ -32,13 +32,13 @@
// and the character used in base64 encoding to represent it.
static class base64_chars {
public:
static constexpr const char to[] =
static constexpr const char* to =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
int8_t from[255];
base64_chars() {
static_assert(sizeof(to) == 64 + 1);
static_assert(strlen(to) == 64);
for (int i = 0; i < 255; i++) {
from[i] = -1; // signal invalid character
from[i] = 255; // signal invalid character
}
for (int i = 0; i < 64; i++) {
from[(unsigned) to[i]] = i;
@@ -77,7 +77,7 @@ std::string base64_encode(bytes_view in) {
return ret;
}
static std::string base64_decode_string(std::string_view in) {
bytes base64_decode(std::string_view in) {
int i = 0;
int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
std::string ret;
@@ -104,42 +104,8 @@ static std::string base64_decode_string(std::string_view in) {
if (i==3)
ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
}
return ret;
}
bytes base64_decode(std::string_view in) {
// FIXME: This copy is sad. The problem is we need back "bytes"
// but "bytes" doesn't have efficient append and std::string.
// To fix this we need to use bytes' "uninitialized" feature.
std::string ret = base64_decode_string(in);
return bytes(ret.begin(), ret.end());
}
static size_t base64_padding_len(std::string_view str) {
size_t padding = 0;
padding += (!str.empty() && str.back() == '=');
padding += (str.size() > 1 && *(str.end() - 2) == '=');
return padding;
}
size_t base64_decoded_len(std::string_view str) {
return str.size() / 4 * 3 - base64_padding_len(str);
}
bool base64_begins_with(std::string_view base, std::string_view operand) {
if (base.size() < operand.size() || base.size() % 4 != 0 || operand.size() % 4 != 0) {
return false;
}
if (base64_padding_len(operand) == 0) {
return base.starts_with(operand);
}
const std::string_view unpadded_base_prefix = base.substr(0, operand.size() - 4);
const std::string_view unpadded_operand = operand.substr(0, operand.size() - 4);
if (unpadded_base_prefix != unpadded_operand) {
return false;
}
// Decode and compare last 4 bytes of base64-encoded strings
const std::string base_remainder = base64_decode_string(base.substr(operand.size() - 4, operand.size()));
const std::string operand_remainder = base64_decode_string(operand.substr(operand.size() - 4));
return base_remainder.starts_with(operand_remainder);
}

View File

@@ -23,7 +23,7 @@
#include <string_view>
#include "bytes.hh"
#include "utils/rjson.hh"
#include "rjson.hh"
std::string base64_encode(bytes_view);
@@ -32,7 +32,3 @@ bytes base64_decode(std::string_view);
inline bytes base64_decode(const rjson::value& v) {
return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
}
size_t base64_decoded_len(std::string_view str);
bool base64_begins_with(std::string_view base, std::string_view operand);

View File

@@ -26,15 +26,10 @@
#include "alternator/error.hh"
#include "cql3/constants.hh"
#include <unordered_map>
#include "utils/rjson.hh"
#include "rjson.hh"
#include "serialization.hh"
#include "base64.hh"
#include <stdexcept>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <boost/algorithm/cxx11/any_of.hpp>
#include "utils/overloaded_functor.hh"
#include "expressions.hh"
namespace alternator {
@@ -57,16 +52,59 @@ comparison_operator_type get_comparison_operator(const rjson::value& comparison_
{"NOT_CONTAINS", comparison_operator_type::NOT_CONTAINS},
};
if (!comparison_operator.IsString()) {
throw api_error::validation(format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
throw api_error("ValidationException", format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
}
std::string op = comparison_operator.GetString();
auto it = ops.find(op);
if (it == ops.end()) {
throw api_error::validation(format("Unsupported comparison operator {}", op));
throw api_error("ValidationException", format("Unsupported comparison operator {}", op));
}
return it->second;
}
static ::shared_ptr<cql3::restrictions::single_column_restriction::contains> make_map_element_restriction(const column_definition& cdef, std::string_view key, const rjson::value& value) {
bytes raw_key = utf8_type->from_string(sstring_view(key.data(), key.size()));
auto key_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_key)));
bytes raw_value = serialize_item(value);
auto entry_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
return make_shared<cql3::restrictions::single_column_restriction::contains>(cdef, std::move(key_value), std::move(entry_value));
}
static ::shared_ptr<cql3::restrictions::single_column_restriction::EQ> make_key_eq_restriction(const column_definition& cdef, const rjson::value& value) {
bytes raw_value = get_key_from_typed_value(value, cdef, type_to_string(cdef.type));
auto restriction_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
return make_shared<cql3::restrictions::single_column_restriction::EQ>(cdef, std::move(restriction_value));
}
::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter) {
clogger.trace("Getting filtering restrictions for: {}", rjson::print(query_filter));
auto filtering_restrictions = ::make_shared<cql3::restrictions::statement_restrictions>(schema, true);
for (auto it = query_filter.MemberBegin(); it != query_filter.MemberEnd(); ++it) {
std::string_view column_name(it->name.GetString(), it->name.GetStringLength());
const rjson::value& condition = it->value;
const rjson::value& comp_definition = rjson::get(condition, "ComparisonOperator");
const rjson::value& attr_list = rjson::get(condition, "AttributeValueList");
comparison_operator_type op = get_comparison_operator(comp_definition);
if (op != comparison_operator_type::EQ) {
throw api_error("ValidationException", "Filtering is currently implemented for EQ operator only");
}
if (attr_list.Size() != 1) {
throw api_error("ValidationException", format("EQ restriction needs exactly 1 attribute value: {}", rjson::print(attr_list)));
}
if (const column_definition* cdef = schema->get_column_definition(to_bytes(column_name.data()))) {
// Primary key restriction
filtering_restrictions->add_restriction(make_key_eq_restriction(*cdef, attr_list[0]), false, true);
} else {
// Regular column restriction
filtering_restrictions->add_restriction(make_map_element_restriction(attrs_col, column_name, attr_list[0]), false, true);
}
}
return filtering_restrictions;
}
namespace {
struct size_check {
@@ -98,16 +136,11 @@ struct nonempty : public size_check {
// Check that array has the expected number of elements
static void verify_operand_count(const rjson::value* array, const size_check& expected, const rjson::value& op) {
if (!array && expected(0)) {
// If expected() allows an empty AttributeValueList, it is also fine
// that it is missing.
return;
}
if (!array || !array->IsArray()) {
throw api_error::validation("With ComparisonOperator, AttributeValueList must be given and an array");
throw api_error("ValidationException", "With ComparisonOperator, AttributeValueList must be given and an array");
}
if (!expected(array->Size())) {
throw api_error::validation(
throw api_error("ValidationException",
format("{} operator requires AttributeValueList {}, instead found list size {}",
op, expected.what(), array->Size()));
}
@@ -131,7 +164,7 @@ static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2
set1_raw.insert(&*it);
}
for (const auto& a : set2.GetArray()) {
if (!set1_raw.contains(&a)) {
if (set1_raw.count(&a) == 0) {
return false;
}
}
@@ -164,11 +197,11 @@ static bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2) {
// binary - otherwise it's a validation error. However, problems with
// the stored attribute (v1) will just return false (no match).
if (!v2.IsObject() || v2.MemberCount() != 1) {
throw api_error::validation(format("BEGINS_WITH operator encountered malformed AttributeValue: {}", v2));
throw api_error("ValidationException", format("BEGINS_WITH operator encountered malformed AttributeValue: {}", v2));
}
auto it2 = v2.MemberBegin();
if (it2->name != "S" && it2->name != "B") {
throw api_error::validation(format("BEGINS_WITH operator requires String or Binary type in AttributeValue, got {}", it2->name));
throw api_error("ValidationException", format("BEGINS_WITH operator requires String or Binary in AttributeValue, got {}", it2->name));
}
@@ -180,25 +213,40 @@ static bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2) {
return false;
}
if (it2->name == "S") {
return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
std::string_view val1(it1->value.GetString(), it1->value.GetStringLength());
std::string_view val2(it2->value.GetString(), it2->value.GetStringLength());
return val1.substr(0, val2.size()) == val2;
} else /* it2->name == "B" */ {
return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
// TODO (optimization): Check the begins_with condition directly on
// the base64-encoded string, without making a decoded copy.
bytes val1 = base64_decode(it1->value);
bytes val2 = base64_decode(it2->value);
return val1.substr(0, val2.size()) == val2;
}
}
static std::string_view to_string_view(const rjson::value& v) {
return std::string_view(v.GetString(), v.GetStringLength());
}
static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
return (type2 == "S" && type1 == "SS") || (type2 == "N" && type1 == "NS") || (type2 == "B" && type1 == "BS");
}
// Check if two JSON-encoded values match with the CONTAINS relation
bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
static bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
if (!v1) {
return false;
}
const auto& kv1 = *v1->MemberBegin();
const auto& kv2 = *v2.MemberBegin();
if (kv2.name != "S" && kv2.name != "N" && kv2.name != "B") {
throw api_error("ValidationException",
format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
"got {} instead", kv2.name));
}
if (kv1.name == "S" && kv2.name == "S") {
return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
return to_string_view(kv1.value).find(to_string_view(kv2.value)) != std::string_view::npos;
} else if (kv1.name == "B" && kv2.name == "B") {
return base64_decode(kv1.value).find(base64_decode(kv2.value)) != bytes::npos;
} else if (is_set_of(kv1.name, kv2.name)) {
@@ -233,12 +281,12 @@ static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
// Check if a JSON-encoded value equals any element of an array, which must have at least one element.
static bool check_IN(const rjson::value* val, const rjson::value& array) {
if (!array[0].IsObject() || array[0].MemberCount() != 1) {
throw api_error::validation(
throw api_error("ValidationException",
format("IN operator encountered malformed AttributeValue: {}", array[0]));
}
const auto& type = array[0].MemberBegin()->name;
if (type != "S" && type != "N" && type != "B") {
throw api_error::validation(
throw api_error("ValidationException",
"IN operator requires AttributeValueList elements to be of type String, Number, or Binary ");
}
if (!val) {
@@ -247,7 +295,7 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
bool have_match = false;
for (const auto& elem : array.GetArray()) {
if (!elem.IsObject() || elem.MemberCount() != 1 || elem.MemberBegin()->name != type) {
throw api_error::validation(
throw api_error("ValidationException",
"IN operator requires all AttributeValueList elements to have the same type ");
}
if (!have_match && *val == elem) {
@@ -258,19 +306,6 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
return have_match;
}
// Another variant of check_IN, this one for ConditionExpression. It needs to
// check whether the first element in the given vector is equal to any of the
// others.
static bool check_IN(const std::vector<rjson::value>& array) {
const rjson::value* first = &array[0];
for (unsigned i = 1; i < array.size(); i++) {
if (check_EQ(first, array[i])) {
return true;
}
}
return false;
}
static bool check_NULL(const rjson::value* val) {
return val == nullptr;
}
@@ -283,13 +318,13 @@ static bool check_NOT_NULL(const rjson::value* val) {
template <typename Comparator>
bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp) {
if (!v2.IsObject() || v2.MemberCount() != 1) {
throw api_error::validation(
throw api_error("ValidationException",
format("{} requires a single AttributeValue of type String, Number, or Binary",
cmp.diagnostic));
}
const auto& kv2 = *v2.MemberBegin();
if (kv2.name != "S" && kv2.name != "N" && kv2.name != "B") {
throw api_error::validation(
throw api_error("ValidationException",
format("{} requires a single AttributeValue of type String, Number, or Binary",
cmp.diagnostic));
}
@@ -316,36 +351,32 @@ bool check_compare(const rjson::value* v1, const rjson::value& v2, const Compara
struct cmp_lt {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs; }
// We cannot use the normal comparison operators like "<" on the bytes
// type, because they treat individual bytes as signed but we need to
// compare them as *unsigned*. So we need a specialization for bytes.
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) < 0; }
static constexpr const char* diagnostic = "LT operator";
};
struct cmp_le {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs <= rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) <= 0; }
// bytes only has <, so we cannot use <=.
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs || lhs == rhs; }
static constexpr const char* diagnostic = "LE operator";
};
struct cmp_ge {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs >= rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) >= 0; }
// bytes only has <, so we cannot use >=.
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return rhs < lhs || lhs == rhs; }
static constexpr const char* diagnostic = "GE operator";
};
struct cmp_gt {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs > rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) > 0; }
// bytes only has <, so we cannot use >.
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return rhs < lhs; }
static constexpr const char* diagnostic = "GT operator";
};
// True if v is between lb and ub, inclusive. Throws if lb > ub.
template <typename T>
static bool check_BETWEEN(const T& v, const T& lb, const T& ub) {
if (cmp_lt()(ub, lb)) {
throw api_error::validation(
bool check_BETWEEN(const T& v, const T& lb, const T& ub) {
if (ub < lb) {
throw api_error("ValidationException",
format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
}
return cmp_ge()(v, lb) && cmp_le()(v, ub);
@@ -356,20 +387,21 @@ static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const r
return false;
}
if (!v->IsObject() || v->MemberCount() != 1) {
throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", *v));
throw api_error("ValidationException", format("BETWEEN operator encountered malformed AttributeValue: {}", *v));
}
if (!lb.IsObject() || lb.MemberCount() != 1) {
throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", lb));
throw api_error("ValidationException", format("BETWEEN operator encountered malformed AttributeValue: {}", lb));
}
if (!ub.IsObject() || ub.MemberCount() != 1) {
throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", ub));
throw api_error("ValidationException", format("BETWEEN operator encountered malformed AttributeValue: {}", ub));
}
const auto& kv_v = *v->MemberBegin();
const auto& kv_lb = *lb.MemberBegin();
const auto& kv_ub = *ub.MemberBegin();
if (kv_lb.name != kv_ub.name) {
throw api_error::validation(
throw api_error(
"ValidationException",
format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
kv_lb.name, kv_ub.name));
}
@@ -388,7 +420,7 @@ static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const r
if (kv_v.name == "B") {
return check_BETWEEN(base64_decode(kv_v.value), base64_decode(kv_lb.value), base64_decode(kv_ub.value));
}
throw api_error::validation(
throw api_error("ValidationException",
format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
kv_lb.name));
}
@@ -408,24 +440,24 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
// and requires a different combinations of parameters in the request
if (value) {
if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
throw api_error::validation("Cannot combine Value with Exists!=true");
throw api_error("ValidationException", "Cannot combine Value with Exists!=true");
}
if (comparison_operator) {
throw api_error::validation("Cannot combine Value with ComparisonOperator");
throw api_error("ValidationException", "Cannot combine Value with ComparisonOperator");
}
return check_EQ(got, *value);
} else if (exists) {
if (comparison_operator) {
throw api_error::validation("Cannot combine Exists with ComparisonOperator");
throw api_error("ValidationException", "Cannot combine Exists with ComparisonOperator");
}
if (!exists->IsBool() || exists->GetBool() != false) {
throw api_error::validation("Exists!=false requires Value");
throw api_error("ValidationException", "Exists!=false requires Value");
}
// Remember Exists=false, so we're checking that the attribute does *not* exist:
return !got;
} else {
if (!comparison_operator) {
throw api_error::validation("Missing ComparisonOperator, Value or Exists");
throw api_error("ValidationException", "Missing ComparisonOperator, Value or Exists");
}
comparison_operator_type op = get_comparison_operator(*comparison_operator);
switch (op) {
@@ -463,188 +495,70 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1]);
case comparison_operator_type::CONTAINS:
{
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
// Expected's "CONTAINS" has this artificial limitation.
// ConditionExpression's "contains()" does not...
const rjson::value& arg = (*attribute_value_list)[0];
const auto& argtype = (*arg.MemberBegin()).name;
if (argtype != "S" && argtype != "N" && argtype != "B") {
throw api_error::validation(
format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
"got {} instead", argtype));
}
return check_CONTAINS(got, arg);
}
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_CONTAINS(got, (*attribute_value_list)[0]);
case comparison_operator_type::NOT_CONTAINS:
{
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
// Expected's "NOT_CONTAINS" has this artificial limitation.
// ConditionExpression's "contains()" does not...
const rjson::value& arg = (*attribute_value_list)[0];
const auto& argtype = (*arg.MemberBegin()).name;
if (argtype != "S" && argtype != "N" && argtype != "B") {
throw api_error::validation(
format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
"got {} instead", argtype));
}
return check_NOT_CONTAINS(got, arg);
}
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_NOT_CONTAINS(got, (*attribute_value_list)[0]);
}
throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
}
}
conditional_operator_type get_conditional_operator(const rjson::value& req) {
const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
if (!conditional_operator) {
return conditional_operator_type::MISSING;
}
if (!conditional_operator->IsString()) {
throw api_error::validation("'ConditionalOperator' parameter, if given, must be a string");
}
auto s = rjson::to_string_view(*conditional_operator);
if (s == "AND") {
return conditional_operator_type::AND;
} else if (s == "OR") {
return conditional_operator_type::OR;
} else {
throw api_error::validation(
format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
}
}
// Check if the existing values of the item (previous_item) match the
// Verify that the existing values of the item (previous_item) match the
// conditions given by the Expected and ConditionalOperator parameters
// (if they exist) in the request (an UpdateItem, PutItem or DeleteItem).
// This function can throw an ValidationException API error if there
// This function will throw a ConditionalCheckFailedException API error
// if the values do not match the condition, or ValidationException if there
// are errors in the format of the condition itself.
bool verify_expected(const rjson::value& req, const rjson::value* previous_item) {
void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item) {
const rjson::value* expected = rjson::find(req, "Expected");
auto conditional_operator = get_conditional_operator(req);
if (conditional_operator != conditional_operator_type::MISSING &&
(!expected || (expected->IsObject() && expected->GetObject().ObjectEmpty()))) {
throw api_error::validation("'ConditionalOperator' parameter cannot be specified for missing or empty Expression");
}
if (!expected) {
return true;
return;
}
if (!expected->IsObject()) {
throw api_error::validation("'Expected' parameter, if given, must be an object");
throw api_error("ValidationException", "'Expected' parameter, if given, must be an object");
}
// ConditionalOperator can be "AND" for requiring all conditions, or
// "OR" for requiring one condition, and defaults to "AND" if missing.
const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
bool require_all = true;
if (conditional_operator) {
if (!conditional_operator->IsString()) {
throw api_error("ValidationException", "'ConditionalOperator' parameter, if given, must be a string");
}
std::string_view s(conditional_operator->GetString(), conditional_operator->GetStringLength());
if (s == "AND") {
// require_all is already true
} else if (s == "OR") {
require_all = false;
} else {
throw api_error("ValidationException", "'ConditionalOperator' parameter must be AND, OR or missing");
}
if (expected->GetObject().ObjectEmpty()) {
throw api_error("ValidationException", "'ConditionalOperator' parameter cannot be specified for empty Expression");
}
}
bool require_all = conditional_operator != conditional_operator_type::OR;
return verify_condition(*expected, require_all, previous_item);
}
bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item) {
for (auto it = condition.MemberBegin(); it != condition.MemberEnd(); ++it) {
for (auto it = expected->MemberBegin(); it != expected->MemberEnd(); ++it) {
const rjson::value* got = nullptr;
if (previous_item) {
got = rjson::find(*previous_item, rjson::to_string_view(it->name));
if (previous_item && previous_item->IsObject() && previous_item->HasMember("Item")) {
got = rjson::find((*previous_item)["Item"], rjson::string_ref_type(it->name.GetString()));
}
bool success = verify_expected_one(it->value, got);
if (success && !require_all) {
// When !require_all, one success is enough!
return true;
return;
} else if (!success && require_all) {
// When require_all, one failure is enough!
return false;
throw api_error("ConditionalCheckFailedException", "Failed condition.");
}
}
// If we got here and require_all, none of the checks failed, so succeed.
// If we got here and !require_all, all of the checks failed, so fail.
return require_all;
}
static bool calculate_primitive_condition(const parsed::primitive_condition& cond,
const rjson::value* previous_item) {
std::vector<rjson::value> calculated_values;
calculated_values.reserve(cond._values.size());
for (const parsed::value& v : cond._values) {
calculated_values.push_back(calculate_value(v,
cond._op == parsed::primitive_condition::type::VALUE ?
calculate_value_caller::ConditionExpressionAlone :
calculate_value_caller::ConditionExpression,
previous_item));
}
switch (cond._op) {
case parsed::primitive_condition::type::BETWEEN:
if (calculated_values.size() != 3) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
}
return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2]);
case parsed::primitive_condition::type::IN:
return check_IN(calculated_values);
case parsed::primitive_condition::type::VALUE:
if (calculated_values.size() != 1) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Unexpected values in primitive_condition", cond._values.size()));
}
// Unwrap the boolean wrapped as the value (if it is a boolean)
if (calculated_values[0].IsObject() && calculated_values[0].MemberCount() == 1) {
auto it = calculated_values[0].MemberBegin();
if (it->name == "BOOL" && it->value.IsBool()) {
return it->value.GetBool();
}
}
throw api_error::validation(
format("ConditionExpression: condition results in a non-boolean value: {}",
calculated_values[0]));
default:
// All the rest of the operators have exactly two parameters (and unless
// we have a bug in the parser, that's what we have in the parsed object:
if (calculated_values.size() != 2) {
throw std::logic_error(format("Wrong number of values {} in primitive_condition object", cond._values.size()));
}
}
switch (cond._op) {
case parsed::primitive_condition::type::EQ:
return check_EQ(&calculated_values[0], calculated_values[1]);
case parsed::primitive_condition::type::NE:
return check_NE(&calculated_values[0], calculated_values[1]);
case parsed::primitive_condition::type::GT:
return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{});
case parsed::primitive_condition::type::GE:
return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{});
case parsed::primitive_condition::type::LT:
return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{});
case parsed::primitive_condition::type::LE:
return check_compare(&calculated_values[0], calculated_values[1], cmp_le{});
default:
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
if (!require_all) {
throw api_error("ConditionalCheckFailedException", "None of ORed Expect conditions were successful.");
}
}
// Check if the existing values of the item (previous_item) match the
// conditions given by the given parsed ConditionExpression.
bool verify_condition_expression(
const parsed::condition_expression& condition_expression,
const rjson::value* previous_item) {
if (condition_expression.empty()) {
return true;
}
bool ret = std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) -> bool {
return calculate_primitive_condition(cond, previous_item);
},
[&] (const parsed::condition_expression::condition_list& list) -> bool {
auto verify_condition = [&] (const parsed::condition_expression& e) {
return verify_condition_expression(e, previous_item);
};
switch (list.op) {
case '&':
return boost::algorithm::all_of(list.conditions, verify_condition);
case '|':
return boost::algorithm::any_of(list.conditions, verify_condition);
default:
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("bad operator in condition_list");
}
}
}, condition_expression._expression);
return condition_expression._negated ? !ret : ret;
}
}

View File

@@ -33,7 +33,6 @@
#include "cql3/restrictions/statement_restrictions.hh"
#include "serialization.hh"
#include "expressions_types.hh"
namespace alternator {
@@ -43,18 +42,8 @@ enum class comparison_operator_type {
comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
enum class conditional_operator_type {
AND, OR, MISSING
};
conditional_operator_type get_conditional_operator(const rjson::value& req);
::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter);
bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
bool verify_condition_expression(
const parsed::condition_expression& condition_expression,
const rjson::value* previous_item);
void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item);
}

View File

@@ -26,15 +26,12 @@
namespace alternator {
// api_error contains a DynamoDB error message to be returned to the user.
// It can be returned by value (see executor::request_return_type) or thrown.
// The DynamoDB's error messages are described in detail in
// DynamoDB's error messages are described in detail in
// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
// An error message has an HTTP code (almost always 400), a type, e.g.,
// "ResourceNotFoundException", and a human readable message.
// Eventually alternator::api_handler will convert a returned or thrown
// api_error into a JSON object, and that is returned to the user.
class api_error final {
// Ah An error message has a "type", e.g., "ResourceNotFoundException", a coarser
// HTTP code (almost always, 400), and a human readable message. Eventually these
// will be wrapped into a JSON object returned to the client.
class api_error : public std::exception {
public:
using status_type = httpd::reply::status_type;
status_type _http_code;
@@ -45,41 +42,8 @@ public:
, _type(std::move(type))
, _msg(std::move(msg))
{ }
// Factory functions for some common types of DynamoDB API errors
static api_error validation(std::string msg) {
return api_error("ValidationException", std::move(msg));
}
static api_error resource_not_found(std::string msg) {
return api_error("ResourceNotFoundException", std::move(msg));
}
static api_error resource_in_use(std::string msg) {
return api_error("ResourceInUseException", std::move(msg));
}
static api_error invalid_signature(std::string msg) {
return api_error("InvalidSignatureException", std::move(msg));
}
static api_error unrecognized_client(std::string msg) {
return api_error("UnrecognizedClientException", std::move(msg));
}
static api_error unknown_operation(std::string msg) {
return api_error("UnknownOperationException", std::move(msg));
}
static api_error access_denied(std::string msg) {
return api_error("AccessDeniedException", std::move(msg));
}
static api_error conditional_check_failed(std::string msg) {
return api_error("ConditionalCheckFailedException", std::move(msg));
}
static api_error expired_iterator(std::string msg) {
return api_error("ExpiredIteratorException", std::move(msg));
}
static api_error trimmed_data_access_exception(std::string msg) {
return api_error("TrimmedDataAccessException", std::move(msg));
}
static api_error internal(std::string msg) {
return api_error("InternalServerError", std::move(msg), reply::status_type::internal_server_error);
}
api_error() = default;
virtual const char* what() const noexcept override { return _msg.c_str(); }
};
}

File diff suppressed because it is too large Load Diff

View File

@@ -25,130 +25,47 @@
#include <seastar/http/httpd.hh>
#include "seastarx.hh"
#include <seastar/json/json_elements.hh>
#include <seastar/core/sharded.hh>
#include "service/storage_proxy.hh"
#include "service/migration_manager.hh"
#include "service/client_state.hh"
#include "db/timeout_clock.hh"
#include "alternator/error.hh"
#include "stats.hh"
#include "utils/rjson.hh"
namespace db {
class system_distributed_keyspace;
}
namespace query {
class partition_slice;
class result;
}
namespace cql3::selection {
class selection;
}
namespace service {
class storage_service;
}
namespace alternator {
class rmw_operation;
struct make_jsonable : public json::jsonable {
rjson::value _value;
public:
explicit make_jsonable(rjson::value&& value);
std::string to_json() const override;
};
struct json_string : public json::jsonable {
std::string _value;
public:
explicit json_string(std::string&& value);
std::string to_json() const override;
};
class executor : public peering_sharded_service<executor> {
class executor {
service::storage_proxy& _proxy;
service::migration_manager& _mm;
db::system_distributed_keyspace& _sdks;
service::storage_service& _ss;
// An smp_service_group to be used for limiting the concurrency when
// forwarding Alternator request between shards - if necessary for LWT.
smp_service_group _ssg;
public:
using client_state = service::client_state;
using request_return_type = std::variant<json::json_return_type, api_error>;
stats _stats;
static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";
static constexpr auto KEYSPACE_NAME = "alternator";
executor(service::storage_proxy& proxy, service::migration_manager& mm, db::system_distributed_keyspace& sdks, service::storage_service& ss, smp_service_group ssg)
: _proxy(proxy), _mm(mm), _sdks(sdks), _ss(ss), _ssg(ssg) {}
executor(service::storage_proxy& proxy, service::migration_manager& mm) : _proxy(proxy), _mm(mm) {}
future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> update_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> list_tables(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> describe_endpoints(client_state& client_state, service_permit permit, rjson::value request, std::string host_header);
future<request_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> list_streams(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> describe_stream(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> get_shard_iterator(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> get_records(client_state& client_state, tracing::trace_state_ptr, service_permit permit, rjson::value request);
future<json::json_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> list_tables(client_state& client_state, std::string content);
future<json::json_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> describe_endpoints(client_state& client_state, std::string content, std::string host_header);
future<json::json_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<json::json_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, std::string content);
future<> start();
future<> stop() { return make_ready_future<>(); }
future<> create_keyspace(std::string_view keyspace_name);
future<> maybe_create_keyspace();
static tracing::trace_state_ptr maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
static sstring table_name(const schema&);
static db::timeout_clock::time_point default_timeout();
static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
private:
friend class rmw_operation;
static bool is_alternator_keyspace(const sstring& ks_name);
static sstring make_keyspace_name(const sstring& table_name);
static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
public:
static std::optional<rjson::value> describe_single_item(schema_ptr,
const query::partition_slice&,
const cql3::selection::selection&,
const query::result&,
const std::unordered_set<std::string>&);
static void describe_single_item(const cql3::selection::selection&,
const std::vector<bytes_opt>&,
const std::unordered_set<std::string>&,
rjson::value&,
bool = false);
void add_stream_options(const rjson::value& stream_spec, schema_builder&) const;
void supplement_table_info(rjson::value& descr, const schema& schema) const;
void supplement_table_stream_info(rjson::value& descr, const schema& schema) const;
};
}

View File

@@ -20,24 +20,15 @@
*/
#include "expressions.hh"
#include "serialization.hh"
#include "base64.hh"
#include "conditions.hh"
#include "alternator/expressionsLexer.hpp"
#include "alternator/expressionsParser.hpp"
#include "utils/overloaded_functor.hh"
#include "error.hh"
#include "seastarx.hh"
#include <seastarx.hh>
#include <seastar/core/print.hh>
#include <seastar/util/log.hh>
#include <boost/algorithm/cxx11/any_of.hpp>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <functional>
#include <unordered_map>
namespace alternator {
@@ -74,19 +65,13 @@ parse_projection_expression(std::string query) {
}
}
parsed::condition_expression
parse_condition_expression(std::string query) {
try {
return do_with_parser(query, std::mem_fn(&expressionsParser::condition_expression));
} catch (...) {
throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
}
}
template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
namespace parsed {
void update_expression::add(update_expression::action a) {
std::visit(overloaded_functor {
std::visit(overloaded {
[&] (action::set&) { seen_set = true; },
[&] (action::remove&) { seen_remove = true; },
[&] (action::add&) { seen_add = true; },
@@ -109,620 +94,5 @@ void update_expression::append(update_expression other) {
seen_del |= other.seen_del;
}
void condition_expression::append(condition_expression&& a, char op) {
std::visit(overloaded_functor {
[&] (condition_list& x) {
// If 'a' has a single condition, we could, instead of inserting
// it insert its single condition (possibly negated if a._negated)
// But considering it we don't evaluate these expressions many
// times, this optimization is not worth extra code complexity.
if (!x.conditions.empty() && x.op != op) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("condition_expression::append called with mixed operators");
}
x.conditions.push_back(std::move(a));
x.op = op;
},
[&] (primitive_condition& x) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("condition_expression::append called on primitive_condition");
}
}, _expression);
}
} // namespace parsed
// The following resolve_*() functions resolve references in parsed
// expressions of different types. Resolving a parsed expression means
// replacing:
// 1. In parsed::path objects, replace references like "#name" with the
// attribute name from ExpressionAttributeNames,
// 2. In parsed::constant objects, replace references like ":value" with
// the value from ExpressionAttributeValues.
// These function also track which name and value references were used, to
// allow complaining if some remain unused.
// Note that the resolve_*() functions modify the expressions in-place,
// so if we ever intend to cache parsed expression, we need to pass a copy
// into this function.
//
// Doing the "resolving" stage before the evaluation stage has two benefits.
// First, it allows us to be compatible with DynamoDB in catching unused
// names and values (see issue #6572). Second, in the FilterExpression case,
// we need to resolve the expression just once but then use it many times
// (once for each item to be filtered).
static void resolve_path(parsed::path& p,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names) {
const std::string& column_name = p.root();
if (column_name.size() > 0 && column_name.front() == '#') {
if (!expression_attribute_names) {
throw api_error::validation(
format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
}
const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
if (!value || !value->IsString()) {
throw api_error::validation(
format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
}
used_attribute_names.emplace(column_name);
p.set_root(std::string(rjson::to_string_view(*value)));
}
}
static void resolve_constant(parsed::constant& c,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (const std::string& valref) {
if (!expression_attribute_values) {
throw api_error::validation(
format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
}
const rjson::value* value = rjson::find(*expression_attribute_values, valref);
if (!value) {
throw api_error::validation(
format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
}
if (value->IsNull()) {
throw api_error::validation(
format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
}
validate_value(*value, "ExpressionAttributeValues");
used_attribute_values.emplace(valref);
c.set(*value);
},
[&] (const parsed::constant::literal& lit) {
// Nothing to do, already resolved
}
}, c._value);
}
void resolve_value(parsed::value& rhs,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (parsed::constant& c) {
resolve_constant(c, expression_attribute_values, used_attribute_values);
},
[&] (parsed::value::function_call& f) {
for (parsed::value& value : f._parameters) {
resolve_value(value, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
},
[&] (parsed::path& p) {
resolve_path(p, expression_attribute_names, used_attribute_names);
}
}, rhs._value);
}
void resolve_set_rhs(parsed::set_rhs& rhs,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
resolve_value(rhs._v1, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
if (rhs._op != 'v') {
resolve_value(rhs._v2, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
void resolve_update_expression(parsed::update_expression& ue,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
for (parsed::update_expression::action& action : ue.actions()) {
resolve_path(action._path, expression_attribute_names, used_attribute_names);
std::visit(overloaded_functor {
[&] (parsed::update_expression::action::set& a) {
resolve_set_rhs(a._rhs, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
},
[&] (parsed::update_expression::action::remove& a) {
// nothing to do
},
[&] (parsed::update_expression::action::add& a) {
resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
},
[&] (parsed::update_expression::action::del& a) {
resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
}
}, action._action);
}
}
static void resolve_primitive_condition(parsed::primitive_condition& pc,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
for (parsed::value& value : pc._values) {
resolve_value(value,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
void resolve_condition_expression(parsed::condition_expression& ce,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (parsed::primitive_condition& cond) {
resolve_primitive_condition(cond,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
},
[&] (parsed::condition_expression::condition_list& list) {
for (parsed::condition_expression& cond : list.conditions) {
resolve_condition_expression(cond,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
}, ce._expression);
}
void resolve_projection_expression(std::vector<parsed::path>& pe,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names) {
for (parsed::path& p : pe) {
resolve_path(p, expression_attribute_names, used_attribute_names);
}
}
// condition_expression_on() checks whether a condition_expression places any
// condition on the given attribute. It can be useful, for example, for
// checking whether the condition tries to restrict a key column.
static bool value_on(const parsed::value& v, std::string_view attribute) {
return std::visit(overloaded_functor {
[&] (const parsed::constant& c) {
return false;
},
[&] (const parsed::value::function_call& f) {
for (const parsed::value& value : f._parameters) {
if (value_on(value, attribute)) {
return true;
}
}
return false;
},
[&] (const parsed::path& p) {
return p.root() == attribute;
}
}, v._value);
}
static bool primitive_condition_on(const parsed::primitive_condition& pc, std::string_view attribute) {
for (const parsed::value& value : pc._values) {
if (value_on(value, attribute)) {
return true;
}
}
return false;
}
bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute) {
return std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) {
return primitive_condition_on(cond, attribute);
},
[&] (const parsed::condition_expression::condition_list& list) {
for (const parsed::condition_expression& cond : list.conditions) {
if (condition_expression_on(cond, attribute)) {
return true;
}
}
return false;
}
}, ce._expression);
}
// for_condition_expression_on() runs a given function over all the attributes
// mentioned in the expression. If the same attribute is mentioned more than
// once, the function will be called more than once for the same attribute.
static void for_value_on(const parsed::value& v, const noncopyable_function<void(std::string_view)>& func) {
std::visit(overloaded_functor {
[&] (const parsed::constant& c) { },
[&] (const parsed::value::function_call& f) {
for (const parsed::value& value : f._parameters) {
for_value_on(value, func);
}
},
[&] (const parsed::path& p) {
func(p.root());
}
}, v._value);
}
void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func) {
std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) {
for (const parsed::value& value : cond._values) {
for_value_on(value, func);
}
},
[&] (const parsed::condition_expression::condition_list& list) {
for (const parsed::condition_expression& cond : list.conditions) {
for_condition_expression_on(cond, func);
}
}
}, ce._expression);
}
// The following calculate_value() functions calculate, or evaluate, a parsed
// expression. The parsed expression is assumed to have been "resolved", with
// the matching resolve_* function.
// Take two JSON-encoded list values (remember that a list value is
// {"L": [...the actual list]}) and return the concatenation, again as
// a list value.
static rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
const rjson::value* list1 = unwrap_list(v1);
const rjson::value* list2 = unwrap_list(v2);
if (!list1 || !list2) {
throw api_error::validation("UpdateExpression: list_append() given a non-list");
}
rjson::value cat = rjson::copy(*list1);
for (const auto& a : list2->GetArray()) {
rjson::push_back(cat, rjson::copy(a));
}
rjson::value ret = rjson::empty_object();
rjson::set(ret, "L", std::move(cat));
return ret;
}
// calculate_size() is ConditionExpression's size() function, i.e., it takes
// a JSON-encoded value and returns its "size" as defined differently for the
// different types - also as a JSON-encoded number.
// It return a JSON-encoded "null" value if this value's type has no size
// defined. Comparisons against this non-numeric value will later fail.
static rjson::value calculate_size(const rjson::value& v) {
// NOTE: If v is improperly formatted for our JSON value encoding, it
// must come from the request itself, not from the database, so it makes
// sense to throw a ValidationException if we see such a problem.
if (!v.IsObject() || v.MemberCount() != 1) {
throw api_error::validation(format("invalid object: {}", v));
}
auto it = v.MemberBegin();
int ret;
if (it->name == "S") {
if (!it->value.IsString()) {
throw api_error::validation(format("invalid string: {}", v));
}
ret = it->value.GetStringLength();
} else if (it->name == "NS" || it->name == "SS" || it->name == "BS" || it->name == "L") {
if (!it->value.IsArray()) {
throw api_error::validation(format("invalid set: {}", v));
}
ret = it->value.Size();
} else if (it->name == "M") {
if (!it->value.IsObject()) {
throw api_error::validation(format("invalid map: {}", v));
}
ret = it->value.MemberCount();
} else if (it->name == "B") {
if (!it->value.IsString()) {
throw api_error::validation(format("invalid byte string: {}", v));
}
ret = base64_decoded_len(rjson::to_string_view(it->value));
} else {
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "null", rjson::value(true));
return json_ret;
}
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "N", rjson::from_string(std::to_string(ret)));
return json_ret;
}
static const rjson::value& calculate_value(const parsed::constant& c) {
return std::visit(overloaded_functor {
[&] (const parsed::constant::literal& v) -> const rjson::value& {
return *v;
},
[&] (const std::string& valref) -> const rjson::value& {
// Shouldn't happen, we should have called resolve_value() earlier
// and replaced the value reference by the literal constant.
throw std::logic_error("calculate_value() called before resolve_value()");
}
}, c._value);
}
static rjson::value to_bool_json(bool b) {
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "BOOL", rjson::value(b));
return json_ret;
}
static bool known_type(std::string_view type) {
static thread_local const std::unordered_set<std::string_view> types = {
"N", "S", "B", "NS", "SS", "BS", "L", "M", "NULL", "BOOL"
};
return types.contains(type);
}
using function_handler_type = rjson::value(calculate_value_caller, const rjson::value*, const parsed::value::function_call&);
static const
std::unordered_map<std::string_view, function_handler_type*> function_handlers {
{"list_append", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::UpdateExpression) {
throw api_error::validation(
format("{}: list_append() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error::validation(
format("{}: list_append() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return list_concatenate(v1, v2);
}
},
{"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::UpdateExpression) {
throw api_error::validation(
format("{}: if_not_exists() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error::validation(
format("{}: if_not_exists() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error::validation(
format("{}: if_not_exists() must include path as its first argument", caller));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return v1.IsNull() ? std::move(v2) : std::move(v1);
}
},
{"size", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpression) {
throw api_error::validation(
format("{}: size() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error::validation(
format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return calculate_size(v);
}
},
{"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error::validation(
format("{}: attribute_exists() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error::validation(
format("{}: attribute_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error::validation(
format("{}: attribute_exists()'s parameter must be a path", caller));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return to_bool_json(!v.IsNull());
}
},
{"attribute_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error::validation(
format("{}: attribute_not_exists() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error::validation(
format("{}: attribute_not_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error::validation(
format("{}: attribute_not_exists()'s parameter must be a path", caller));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return to_bool_json(v.IsNull());
}
},
{"attribute_type", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error::validation(
format("{}: attribute_type() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error::validation(
format("{}: attribute_type() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
// There is no real reason for the following check (not
// allowing the type to come from a document attribute), but
// DynamoDB does this check, so we do too...
if (!f._parameters[1].is_constant()) {
throw api_error::validation(
format("{}: attribute_types()'s first parameter must be an expression attribute", caller));
}
rjson::value v0 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v1 = calculate_value(f._parameters[1], caller, previous_item);
if (v1.IsObject() && v1.MemberCount() == 1 && v1.MemberBegin()->name == "S") {
// If the type parameter is not one of the legal types
// we should generate an error, not a failed condition:
if (!known_type(rjson::to_string_view(v1.MemberBegin()->value))) {
throw api_error::validation(
format("{}: attribute_types()'s second parameter, {}, is not a known type",
caller, v1.MemberBegin()->value));
}
if (v0.IsObject() && v0.MemberCount() == 1) {
return to_bool_json(v1.MemberBegin()->value == v0.MemberBegin()->name);
} else {
return to_bool_json(false);
}
} else {
throw api_error::validation(
format("{}: attribute_type() second parameter must refer to a string, got {}", caller, v1));
}
}
},
{"begins_with", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error::validation(
format("{}: begins_with() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error::validation(
format("{}: begins_with() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
// TODO: There's duplication here with check_BEGINS_WITH().
// But unfortunately, the two functions differ a bit.
// If one of v1 or v2 is malformed or has an unsupported type
// (not B or S), what we do depends on whether it came from
// the user's query (is_constant()), or the item. Unsupported
// values in the query result in an error, but if they are in
// the item, we silently return false (no match).
bool bad = false;
if (!v1.IsObject() || v1.MemberCount() != 1) {
bad = true;
if (f._parameters[0].is_constant()) {
throw api_error::validation(format("{}: begins_with() encountered malformed AttributeValue: {}", caller, v1));
}
} else if (v1.MemberBegin()->name != "S" && v1.MemberBegin()->name != "B") {
bad = true;
if (f._parameters[0].is_constant()) {
throw api_error::validation(format("{}: begins_with() supports only string or binary in AttributeValue: {}", caller, v1));
}
}
if (!v2.IsObject() || v2.MemberCount() != 1) {
bad = true;
if (f._parameters[1].is_constant()) {
throw api_error::validation(format("{}: begins_with() encountered malformed AttributeValue: {}", caller, v2));
}
} else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
bad = true;
if (f._parameters[1].is_constant()) {
throw api_error::validation(format("{}: begins_with() supports only string or binary in AttributeValue: {}", caller, v2));
}
}
bool ret = false;
if (!bad) {
auto it1 = v1.MemberBegin();
auto it2 = v2.MemberBegin();
if (it1->name == it2->name) {
if (it2->name == "S") {
std::string_view val1 = rjson::to_string_view(it1->value);
std::string_view val2 = rjson::to_string_view(it2->value);
ret = val1.starts_with(val2);
} else /* it2->name == "B" */ {
ret = base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
}
}
}
return to_bool_json(ret);
}
},
{"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error::validation(
format("{}: contains() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error::validation(
format("{}: contains() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1, v2));
}
},
};
// Given a parsed::value, which can refer either to a constant value from
// ExpressionAttributeValues, to the value of some attribute, or to a function
// of other values, this function calculates the resulting value.
// "caller" determines which expression - ConditionExpression or
// UpdateExpression - is asking for this value. We need to know this because
// DynamoDB allows a different choice of functions for different expressions.
rjson::value calculate_value(const parsed::value& v,
calculate_value_caller caller,
const rjson::value* previous_item) {
return std::visit(overloaded_functor {
[&] (const parsed::constant& c) -> rjson::value {
return rjson::copy(calculate_value(c));
},
[&] (const parsed::value::function_call& f) -> rjson::value {
auto function_it = function_handlers.find(std::string_view(f._function_name));
if (function_it == function_handlers.end()) {
throw api_error::validation(
format("UpdateExpression: unknown function '{}' called.", f._function_name));
}
return function_it->second(caller, previous_item, f);
},
[&] (const parsed::path& p) -> rjson::value {
if (!previous_item) {
return rjson::null_value();
}
std::string update_path = p.root();
if (p.has_operators()) {
// FIXME: support this
throw api_error::validation("Reading attribute paths not yet implemented");
}
const rjson::value* previous_value = rjson::find(*previous_item, update_path);
return previous_value ? rjson::copy(*previous_value) : rjson::null_value();
}
}, v._value);
}
// Same as calculate_value() above, except takes a set_rhs, which may be
// either a single value, or v1+v2 or v1-v2.
rjson::value calculate_value(const parsed::set_rhs& rhs,
const rjson::value* previous_item) {
switch (rhs._op) {
case 'v':
return calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
case '+': {
rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
return number_add(v1, v2);
}
case '-': {
rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
return number_subtract(v1, v2);
}
}
// Can't happen
return rjson::null_value();
}
} // namespace alternator

View File

@@ -145,12 +145,6 @@ REMOVE: R E M O V E;
ADD: A D D;
DELETE: D E L E T E;
AND: A N D;
OR: O R;
NOT: N O T;
BETWEEN: B E T W E E N;
IN: I N;
fragment ALPHA: 'A'..'Z' | 'a'..'z';
fragment DIGIT: '0'..'9';
fragment ALNUM: ALPHA | DIGIT | '_';
@@ -171,19 +165,19 @@ path returns [parsed::path p]:
| '[' INTEGER ']' { $p.add_index(std::stoi($INTEGER.text)); }
)*;
value returns [parsed::value v]:
VALREF { $v.set_valref($VALREF.text); }
| path { $v.set_path($path.p); }
| NAME { $v.set_func_name($NAME.text); }
'(' x=value { $v.add_func_parameter($x.v); }
(',' x=value { $v.add_func_parameter($x.v); })*
update_expression_set_value returns [parsed::value v]:
VALREF { $v.set_valref($VALREF.text); }
| path { $v.set_path($path.p); }
| NAME { $v.set_func_name($NAME.text); }
'(' x=update_expression_set_value { $v.add_func_parameter($x.v); }
(',' x=update_expression_set_value { $v.add_func_parameter($x.v); })*
')'
;
update_expression_set_rhs returns [parsed::set_rhs rhs]:
v=value { $rhs.set_value(std::move($v.v)); }
( '+' v=value { $rhs.set_plus(std::move($v.v)); }
| '-' v=value { $rhs.set_minus(std::move($v.v)); }
v=update_expression_set_value { $rhs.set_value(std::move($v.v)); }
( '+' v=update_expression_set_value { $rhs.set_plus(std::move($v.v)); }
| '-' v=update_expression_set_value { $rhs.set_minus(std::move($v.v)); }
)?
;
@@ -218,48 +212,3 @@ update_expression returns [parsed::update_expression e]:
projection_expression returns [std::vector<parsed::path> v]:
p=path { $v.push_back(std::move($p.p)); }
(',' p=path { $v.push_back(std::move($p.p)); } )* EOF;
primitive_condition returns [parsed::primitive_condition c]:
v=value { $c.add_value(std::move($v.v));
$c.set_operator(parsed::primitive_condition::type::VALUE); }
( ( '=' { $c.set_operator(parsed::primitive_condition::type::EQ); }
| '<' '>' { $c.set_operator(parsed::primitive_condition::type::NE); }
| '<' { $c.set_operator(parsed::primitive_condition::type::LT); }
| '<' '=' { $c.set_operator(parsed::primitive_condition::type::LE); }
| '>' { $c.set_operator(parsed::primitive_condition::type::GT); }
| '>' '=' { $c.set_operator(parsed::primitive_condition::type::GE); }
)
v=value { $c.add_value(std::move($v.v)); }
| BETWEEN { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
v=value { $c.add_value(std::move($v.v)); }
AND
v=value { $c.add_value(std::move($v.v)); }
| IN '(' { $c.set_operator(parsed::primitive_condition::type::IN); }
v=value { $c.add_value(std::move($v.v)); }
(',' v=value { $c.add_value(std::move($v.v)); })*
')'
)?
;
// The following rules for parsing boolean expressions are verbose and
// somewhat strange because of Antlr 3's limitations on recursive rules,
// common rule prefixes, and (lack of) support for operator precedence.
// These rules could have been written more clearly using a more powerful
// parser generator - such as Yacc.
boolean_expression returns [parsed::condition_expression e]:
b=boolean_expression_1 { $e.append(std::move($b.e), '|'); }
(OR b=boolean_expression_1 { $e.append(std::move($b.e), '|'); } )*
;
boolean_expression_1 returns [parsed::condition_expression e]:
b=boolean_expression_2 { $e.append(std::move($b.e), '&'); }
(AND b=boolean_expression_2 { $e.append(std::move($b.e), '&'); } )*
;
boolean_expression_2 returns [parsed::condition_expression e]:
p=primitive_condition { $e.set_primitive(std::move($p.c)); }
| NOT b=boolean_expression_2 { $e = std::move($b.e); $e.apply_not(); }
| '(' b=boolean_expression ')' { $e = std::move($b.e); }
;
condition_expression returns [parsed::condition_expression e]:
boolean_expression { e=std::move($boolean_expression.e); } EOF;

View File

@@ -24,13 +24,8 @@
#include <string>
#include <stdexcept>
#include <vector>
#include <unordered_set>
#include <string_view>
#include <seastar/util/noncopyable_function.hh>
#include "expressions_types.hh"
#include "utils/rjson.hh"
namespace alternator {
@@ -41,62 +36,6 @@ public:
parsed::update_expression parse_update_expression(std::string query);
std::vector<parsed::path> parse_projection_expression(std::string query);
parsed::condition_expression parse_condition_expression(std::string query);
void resolve_update_expression(parsed::update_expression& ue,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values);
void resolve_projection_expression(std::vector<parsed::path>& pe,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names);
void resolve_condition_expression(parsed::condition_expression& ce,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values);
void validate_value(const rjson::value& v, const char* caller);
bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute);
// for_condition_expression_on() runs the given function on the attributes
// that the expression uses. It may run for the same attribute more than once
// if the same attribute is used more than once in the expression.
void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func);
// calculate_value() behaves slightly different (especially, different
// functions supported) when used in different types of expressions, as
// enumerated in this enum:
enum class calculate_value_caller {
UpdateExpression, ConditionExpression, ConditionExpressionAlone
};
inline std::ostream& operator<<(std::ostream& out, calculate_value_caller caller) {
switch (caller) {
case calculate_value_caller::UpdateExpression:
out << "UpdateExpression";
break;
case calculate_value_caller::ConditionExpression:
out << "ConditionExpression";
break;
case calculate_value_caller::ConditionExpressionAlone:
out << "ConditionExpression";
break;
default:
out << "unknown type of expression";
break;
}
return out;
}
rjson::value calculate_value(const parsed::value& v,
calculate_value_caller caller,
const rjson::value* previous_item);
rjson::value calculate_value(const parsed::set_rhs& rhs,
const rjson::value* previous_item);
} /* namespace alternator */

View File

@@ -25,10 +25,6 @@
#include <string>
#include <variant>
#include <seastar/core/shared_ptr.hh>
#include "utils/rjson.hh"
/*
* Parsed representation of expressions and their components.
*
@@ -67,27 +63,10 @@ public:
}
};
// When an expression is first parsed, all constants are references, like
// ":val1", into ExpressionAttributeValues. This uses std::string() variant.
// The resolve_value() function replaces these constants by the JSON item
// extracted from the ExpressionAttributeValues.
struct constant {
// We use lw_shared_ptr<rjson::value> just to make rjson::value copyable,
// to make this entire object copyable as ANTLR needs.
using literal = lw_shared_ptr<rjson::value>;
std::variant<std::string, literal> _value;
void set(const rjson::value& v) {
_value = make_lw_shared<rjson::value>(rjson::copy(v));
}
void set(std::string& s) {
_value = s;
}
};
// "value" is is a value used in the right hand side of an assignment
// expression, "SET a = ...". It can be a constant (a reference to a value
// included in the request, e.g., ":val"), a path to an attribute from the
// existing item (e.g., "a.b[3].c"), or a function of other such values.
// expression, "SET a = ...". It can be a reference to a value included in
// the request (":val"), a path to an attribute from the existing item
// (e.g., "a.b[3].c"), or a function of other such values.
// Note that the real right-hand-side of an assignment is actually a bit
// more general - it allows either a value, or a value+value or value-value -
// see class set_rhs below.
@@ -96,12 +75,9 @@ struct value {
std::string _function_name;
std::vector<value> _parameters;
};
std::variant<constant, path, function_call> _value;
void set_constant(constant c) {
_value = std::move(c);
}
std::variant<std::string, path, function_call> _value;
void set_valref(std::string s) {
_value = constant { std::move(s) };
_value = std::move(s);
}
void set_path(path p) {
_value = std::move(p);
@@ -112,15 +88,6 @@ struct value {
void add_func_parameter(value v) {
std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
}
bool is_constant() const {
return std::holds_alternative<constant>(_value);
}
bool is_path() const {
return std::holds_alternative<path>(_value);
}
bool is_func() const {
return std::holds_alternative<function_call>(_value);
}
};
// The right-hand-side of a SET in an update expression can be either a
@@ -154,10 +121,10 @@ public:
struct remove {
};
struct add {
constant _valref;
std::string _valref;
};
struct del {
constant _valref;
std::string _valref;
};
std::variant<set, remove, add, del> _action;
@@ -171,11 +138,11 @@ public:
}
void assign_add(path p, std::string v) {
_path = std::move(p);
_action = add { constant { std::move(v) } };
_action = add { std::move(v) };
}
void assign_del(path p, std::string v) {
_path = std::move(p);
_action = del { constant { std::move(v) } };
_action = del { std::move(v) };
}
};
private:
@@ -193,62 +160,6 @@ public:
const std::vector<action>& actions() const {
return _actions;
}
std::vector<action>& actions() {
return _actions;
}
};
// A primitive_condition is a condition expression involving one condition,
// while the full condition_expression below adds boolean logic over these
// primitive conditions.
// The supported primitive conditions are:
// 1. Binary operators - v1 OP v2, where OP is =, <>, <, <=, >, or >= and
// v1 and v2 are values - from the item (an attribute path), the query
// (a ":val" reference), or a function of the the above (only the size()
// function is supported).
// 2. Ternary operator - v1 BETWEEN v2 and v3 (means v1 >= v2 AND v1 <= v3).
// 3. N-ary operator - v1 IN ( v2, v3, ... )
// 4. A single function call (attribute_exists etc.). The parser actually
// accepts a more general "value" here but later stages reject a value
// which is not a function call (because DynamoDB does it too).
class primitive_condition {
public:
enum class type {
UNDEFINED, VALUE, EQ, NE, LT, LE, GT, GE, BETWEEN, IN
};
type _op = type::UNDEFINED;
std::vector<value> _values;
void set_operator(type op) {
_op = op;
}
void add_value(value&& v) {
_values.push_back(std::move(v));
}
bool empty() const {
return _op == type::UNDEFINED;
}
};
class condition_expression {
public:
bool _negated = false; // If true, the entire condition is negated
struct condition_list {
char op = '|'; // '&' or '|'
std::vector<condition_expression> conditions;
};
std::variant<primitive_condition, condition_list> _expression = condition_list();
void set_primitive(primitive_condition&& p) {
_expression = std::move(p);
}
void append(condition_expression&& c, char op);
void apply_not() {
_negated = !_negated;
}
bool empty() const {
return std::holds_alternative<condition_list>(_expression) &&
std::get<condition_list>(_expression).conditions.empty();
}
};
} // namespace parsed

172
alternator/rjson.cc Normal file
View File

@@ -0,0 +1,172 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "rjson.hh"
#include "error.hh"
#include <seastar/core/print.hh>
namespace rjson {
static allocator the_allocator;
std::string print(const rjson::value& value) {
string_buffer buffer;
writer writer(buffer);
value.Accept(writer);
return std::string(buffer.GetString());
}
rjson::value copy(const rjson::value& value) {
return rjson::value(value, the_allocator);
}
rjson::value parse(const std::string& str) {
return parse_raw(str.c_str(), str.size());
}
rjson::value parse_raw(const char* c_str, size_t size) {
rjson::document d;
d.Parse(c_str, size);
if (d.HasParseError()) {
throw rjson::error(format("Parsing JSON failed: {}", GetParseError_En(d.GetParseError())));
}
rjson::value& v = d;
return std::move(v);
}
rjson::value& get(rjson::value& value, rjson::string_ref_type name) {
auto member_it = value.FindMember(name);
if (member_it != value.MemberEnd())
return member_it->value;
else {
throw rjson::error(format("JSON parameter {} not found", name));
}
}
const rjson::value& get(const rjson::value& value, rjson::string_ref_type name) {
auto member_it = value.FindMember(name);
if (member_it != value.MemberEnd())
return member_it->value;
else {
throw rjson::error(format("JSON parameter {} not found", name));
}
}
rjson::value from_string(const std::string& str) {
return rjson::value(str.c_str(), str.size(), the_allocator);
}
rjson::value from_string(const sstring& str) {
return rjson::value(str.c_str(), str.size(), the_allocator);
}
rjson::value from_string(const char* str, size_t size) {
return rjson::value(str, size, the_allocator);
}
const rjson::value* find(const rjson::value& value, string_ref_type name) {
auto member_it = value.FindMember(name);
return member_it != value.MemberEnd() ? &member_it->value : nullptr;
}
rjson::value* find(rjson::value& value, string_ref_type name) {
auto member_it = value.FindMember(name);
return member_it != value.MemberEnd() ? &member_it->value : nullptr;
}
void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member) {
base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), std::move(member), the_allocator);
}
void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member) {
base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), rjson::value(member), the_allocator);
}
void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member) {
base.AddMember(name, std::move(member), the_allocator);
}
void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member) {
base.AddMember(name, rjson::value(member), the_allocator);
}
void push_back(rjson::value& base_array, rjson::value&& item) {
base_array.PushBack(std::move(item), the_allocator);
}
bool single_value_comp::operator()(const rjson::value& r1, const rjson::value& r2) const {
auto r1_type = r1.GetType();
auto r2_type = r2.GetType();
// null is the smallest type and compares with every other type, nothing is lesser than null
if (r1_type == rjson::type::kNullType || r2_type == rjson::type::kNullType) {
return r1_type < r2_type;
}
// only null, true, and false are comparable with each other, other types are not compatible
if (r1_type != r2_type) {
if (r1_type > rjson::type::kTrueType || r2_type > rjson::type::kTrueType) {
throw rjson::error(format("Types are not comparable: {} {}", r1, r2));
}
}
switch (r1_type) {
case rjson::type::kNullType:
// fall-through
case rjson::type::kFalseType:
// fall-through
case rjson::type::kTrueType:
return r1_type < r2_type;
case rjson::type::kObjectType:
throw rjson::error("Object type comparison is not supported");
case rjson::type::kArrayType:
throw rjson::error("Array type comparison is not supported");
case rjson::type::kStringType: {
const size_t r1_len = r1.GetStringLength();
const size_t r2_len = r2.GetStringLength();
size_t len = std::min(r1_len, r2_len);
int result = std::strncmp(r1.GetString(), r2.GetString(), len);
return result < 0 || (result == 0 && r1_len < r2_len);
}
case rjson::type::kNumberType: {
if (r1.IsInt() && r2.IsInt()) {
return r1.GetInt() < r2.GetInt();
} else if (r1.IsUint() && r2.IsUint()) {
return r1.GetUint() < r2.GetUint();
} else if (r1.IsInt64() && r2.IsInt64()) {
return r1.GetInt64() < r2.GetInt64();
} else if (r1.IsUint64() && r2.IsUint64()) {
return r1.GetUint64() < r2.GetUint64();
} else {
// it's safe to call GetDouble() on any number type
return r1.GetDouble() < r2.GetDouble();
}
}
default:
return false;
}
}
} // end namespace rjson
std::ostream& std::operator<<(std::ostream& os, const rjson::value& v) {
return os << rjson::print(v);
}

View File

@@ -80,21 +80,6 @@ using string_buffer = rapidjson::GenericStringBuffer<encoding>;
using writer = rapidjson::Writer<string_buffer, encoding>;
using type = rapidjson::Type;
/**
* exception specializations.
*/
class malformed_value : public error {
public:
malformed_value(std::string_view name, const rjson::value& value);
malformed_value(std::string_view name, std::string_view value);
};
class missing_value : public error {
public:
missing_value(std::string_view name);
};
// Returns an object representing JSON's null
inline rjson::value null_value() {
return rjson::value(rapidjson::kNullType);
@@ -119,81 +104,38 @@ inline rjson::value empty_string() {
// The representation is dense - without any redundant indentation.
std::string print(const rjson::value& value);
// Returns a string_view to the string held in a JSON value (which is
// assumed to hold a string, i.e., v.IsString() == true). This is a view
// to the existing data - no copying is done.
inline std::string_view to_string_view(const rjson::value& v) {
return std::string_view(v.GetString(), v.GetStringLength());
}
// Copies given JSON value - involves allocation
rjson::value copy(const rjson::value& value);
// Parses a JSON value from given string or raw character array.
// The string/char array liveness does not need to be persisted,
// as parse() will allocate member names and values.
// as both parse() and parse_raw() will allocate member names and values.
// Throws rjson::error if parsing failed.
rjson::value parse(std::string_view str);
// Parses a JSON value returns a disengaged optional on failure.
// NOTICE: any error context will be lost, so this function should
// be used only if one does not care why parsing failed.
std::optional<rjson::value> try_parse(std::string_view str);
// Needs to be run in thread context
rjson::value parse_yieldable(std::string_view str);
rjson::value parse(const std::string& str);
rjson::value parse_raw(const char* c_str, size_t size);
// Creates a JSON value (of JSON string type) out of internal string representations.
// The string value is copied, so str's liveness does not need to be persisted.
rjson::value from_string(const std::string& str);
rjson::value from_string(const sstring& str);
rjson::value from_string(const char* str, size_t size);
rjson::value from_string(std::string_view view);
// Returns a pointer to JSON member if it exists, nullptr otherwise
rjson::value* find(rjson::value& value, std::string_view name);
const rjson::value* find(const rjson::value& value, std::string_view name);
rjson::value* find(rjson::value& value, rjson::string_ref_type name);
const rjson::value* find(const rjson::value& value, rjson::string_ref_type name);
// Returns a reference to JSON member if it exists, throws otherwise
rjson::value& get(rjson::value& value, std::string_view name);
const rjson::value& get(const rjson::value& value, std::string_view name);
/**
* Type conversion getter.
* Will typically require an existing rapidjson::internal::TypeHelper<...>
* to exist for the type queried.
*/
template<typename T>
T get(const rjson::value& value, std::string_view name) {
auto& v = get(value, name);
try {
return v.Get<T>();
} catch (...) {
std::throw_with_nested(malformed_value(name, v));
}
}
/**
* Type conversion opt getter.
* Will typically require an existing rapidjson::internal::TypeHelper<...>
* to exist for the type queried.
*
* Return std::nullopt if value does not exist.
*/
template<typename T>
std::optional<T> get_opt(const rjson::value& value, std::string_view name) {
auto* v = find(value, name);
try {
return v ? std::optional<T>(v->Get<T>()) : std::nullopt;
} catch (...) {
std::throw_with_nested(malformed_value(name, *v));
}
}
rjson::value& get(rjson::value& value, rjson::string_ref_type name);
const rjson::value& get(const rjson::value& value, rjson::string_ref_type name);
// Sets a member in given JSON object by moving the member - allocates the name.
// Throws if base is not a JSON object.
void set_with_string_name(rjson::value& base, std::string_view name, rjson::value&& member);
void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member);
// Sets a string member in given JSON object by assigning its reference - allocates the name.
// NOTICE: member string liveness must be ensured to be at least as long as base's.
// Throws if base is not a JSON object.
void set_with_string_name(rjson::value& base, std::string_view name, rjson::string_ref_type member);
void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member);
// Sets a member in given JSON object by moving the member.
// NOTICE: name liveness must be ensured to be at least as long as base's.
@@ -206,67 +148,14 @@ void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member)
// Throws if base is not a JSON object.
void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member);
/**
* Type conversion setter.
* Will typically require an existing rapidjson::internal::TypeHelper<...>
* to exist for the type written.
*
* (Note: order is important. Need to be after set(..., rjson::value),
* otherwise the enable_if must be expanded)
*/
template<typename T>
std::enable_if_t<!std::is_constructible_v<string_ref_type, T>>
set(rjson::value& base, rjson::string_ref_type name, T&& member) {
extern allocator the_allocator;
rjson::value v;
v.Set(std::forward<T>(member), the_allocator);
set(base, std::move(name), std::move(v));
}
// Adds a value to a JSON list by moving the item to its end.
// Throws if base_array is not a JSON array.
void push_back(rjson::value& base_array, rjson::value&& item);
// Remove a member from a JSON object. Throws if value isn't an object.
bool remove_member(rjson::value& value, std::string_view name);
struct single_value_comp {
bool operator()(const rjson::value& r1, const rjson::value& r2) const;
};
// Helper function for parsing a JSON straight into a map
// of strings representing their values - useful for various
// database helper functions.
// This function exists for historical reasons - existing infrastructure
// relies on being able to transform a JSON string into a map of sstrings.
template<typename Map>
requires (std::is_same_v<Map, std::map<sstring, sstring>> || std::is_same_v<Map, std::unordered_map<sstring, sstring>>)
Map parse_to_map(std::string_view raw) {
Map map;
rjson::value root = rjson::parse(raw);
if (root.IsNull()) {
return map;
}
if (!root.IsObject()) {
throw rjson::error("Only json objects can be transformed to maps. Encountered: " + std::string(raw));
}
for (auto it = root.MemberBegin(); it != root.MemberEnd(); ++it) {
if (it->value.IsString()) {
map.emplace(sstring(rjson::to_string_view(it->name)), sstring(rjson::to_string_view(it->value)));
} else {
map.emplace(sstring(rjson::to_string_view(it->name)), sstring(rjson::print(it->value)));
}
}
return map;
}
// This function exists for historical reasons as well.
rjson::value from_string_map(const std::map<sstring, sstring>& map);
// The function operates on sstrings for historical reasons.
sstring quote_json_string(const sstring& value);
} // end namespace rjson
namespace std {

View File

@@ -1,128 +0,0 @@
/*
* Copyright 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "seastarx.hh"
#include "service/storage_proxy.hh"
#include "service/storage_proxy.hh"
#include "utils/rjson.hh"
#include "executor.hh"
namespace alternator {
// An rmw_operation encapsulates the common logic of all the item update
// operations which may involve a read of the item before the write
// (so-called Read-Modify-Write operations). These operations include PutItem,
// UpdateItem and DeleteItem: All of these may be conditional operations (the
// "Expected" parameter) which requir a read before the write, and UpdateItem
// may also have an update expression which refers to the item's old value.
//
// The code below supports running the read and the write together as one
// transaction using LWT (this is why rmw_operation is a subclass of
// cas_request, as required by storage_proxy::cas()), but also has optional
// modes not using LWT.
class rmw_operation : public service::cas_request, public enable_shared_from_this<rmw_operation> {
public:
// The following options choose which mechanism to use for isolating
// parallel write operations:
// * The FORBID_RMW option forbids RMW (read-modify-write) operations
// such as conditional updates. For the remaining write-only
// operations, ordinary quorum writes are isolated enough.
// * The LWT_ALWAYS option always uses LWT (lightweight transactions)
// for any write operation - whether or not it also has a read.
// * The LWT_RMW_ONLY option uses LWT only for RMW operations, and uses
// ordinary quorum writes for write-only operations.
// This option is not safe if the user may send both RMW and write-only
// operations on the same item.
// * The UNSAFE_RMW option does read-modify-write operations as separate
// read and write. It is unsafe - concurrent RMW operations are not
// isolated at all. This option will likely be removed in the future.
enum class write_isolation {
FORBID_RMW, LWT_ALWAYS, LWT_RMW_ONLY, UNSAFE_RMW
};
static constexpr auto WRITE_ISOLATION_TAG_KEY = "system:write_isolation";
static write_isolation get_write_isolation_for_schema(schema_ptr schema);
static write_isolation default_write_isolation;
public:
static void set_default_write_isolation(std::string_view mode);
protected:
// The full request JSON
rjson::value _request;
// All RMW operations involve a single item with a specific partition
// and optional clustering key, in a single table, so the following
// information is common to all of them:
schema_ptr _schema;
partition_key _pk = partition_key::make_empty();
clustering_key _ck = clustering_key::make_empty();
write_isolation _write_isolation;
// All RMW operations can have a ReturnValues parameter from the following
// choices. But note that only UpdateItem actually supports all of them:
enum class returnvalues {
NONE, ALL_OLD, UPDATED_OLD, ALL_NEW, UPDATED_NEW
} _returnvalues;
static returnvalues parse_returnvalues(const rjson::value& request);
// When _returnvalues != NONE, apply() should store here, in JSON form,
// the values which are to be returned in the "Attributes" field.
// The default null JSON means do not return an Attributes field at all.
// This field is marked "mutable" so that the const apply() can modify
// it (see explanation below), but note that because apply() may be
// called more than once, if apply() will sometimes set this field it
// must set it (even if just to the default empty value) every time.
mutable rjson::value _return_attributes;
public:
// The constructor of a rmw_operation subclass should parse the request
// and try to discover as many input errors as it can before really
// attempting the read or write operations.
rmw_operation(service::storage_proxy& proxy, rjson::value&& request);
// rmw_operation subclasses (update_item_operation, put_item_operation
// and delete_item_operation) shall implement an apply() function which
// takes the previous value of the item (if it was read) and creates the
// write mutation. If the previous value of item does not pass the needed
// conditional expression, apply() should return an empty optional.
// apply() may throw if it encounters input errors not discovered during
// the constructor.
// apply() may be called more than once in case of contention, so it must
// not change the state saved in the object (issue #7218 was caused by
// violating this). We mark apply() "const" to let the compiler validate
// this for us. The output-only field _return_attributes is marked
// "mutable" above so that apply() can still write to it.
virtual std::optional<mutation> apply(std::unique_ptr<rjson::value> previous_item, api::timestamp_type ts) const = 0;
// Convert the above apply() into the signature needed by cas_request:
virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts) override;
virtual ~rmw_operation() = default;
schema_ptr schema() const { return _schema; }
const rjson::value& request() const { return _request; }
rjson::value&& move_request() && { return std::move(_request); }
future<executor::request_return_type> execute(service::storage_proxy& proxy,
service::client_state& client_state,
tracing::trace_state_ptr trace_state,
service_permit permit,
bool needs_read_before_write,
stats& stats);
std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
};
} // namespace alternator

View File

@@ -31,8 +31,8 @@ static logging::logger slogger("alternator-serialization");
namespace alternator {
type_info type_info_from_string(std::string_view type) {
static thread_local const std::unordered_map<std::string_view, type_info> type_infos = {
type_info type_info_from_string(std::string type) {
static thread_local const std::unordered_map<std::string, type_info> type_infos = {
{"S", {alternator_type::S, utf8_type}},
{"B", {alternator_type::B, bytes_type}},
{"BOOL", {alternator_type::BOOL, boolean_type}},
@@ -65,7 +65,7 @@ struct from_json_visitor {
void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), from_json_visitor{v, bo}); };
void operator()(const string_type_impl& t) {
bo.write(t.from_string(rjson::to_string_view(v)));
bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
}
void operator()(const bytes_type_impl& t) const {
bo.write(base64_decode(v));
@@ -74,27 +74,23 @@ struct from_json_visitor {
bo.write(boolean_type->decompose(v.GetBool()));
}
void operator()(const decimal_type_impl& t) const {
try {
bo.write(t.from_string(rjson::to_string_view(v)));
} catch (const marshal_exception& e) {
throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", v));
}
bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
}
// default
void operator()(const abstract_type& t) const {
bo.write(from_json_object(t, v, cql_serialization_format::internal()));
bo.write(from_json_object(t, Json::Value(rjson::print(v)), cql_serialization_format::internal()));
}
};
bytes serialize_item(const rjson::value& item) {
if (item.IsNull() || item.MemberCount() != 1) {
throw api_error::validation(format("An item can contain only one attribute definition: {}", item));
throw api_error("ValidationException", format("An item can contain only one attribute definition: {}", item));
}
auto it = item.MemberBegin();
type_info type_info = type_info_from_string(rjson::to_string_view(it->name)); // JSON keys are guaranteed to be strings
type_info type_info = type_info_from_string(it->name.GetString()); // JSON keys are guaranteed to be strings
if (type_info.atype == alternator_type::NOT_SUPPORTED_YET) {
slogger.trace("Non-optimal serialization of type {}", it->name);
slogger.trace("Non-optimal serialization of type {}", it->name.GetString());
return bytes{int8_t(type_info.atype)} + to_bytes(rjson::print(item));
}
@@ -125,14 +121,14 @@ struct to_json_visitor {
}
// default
void operator()(const abstract_type& t) const {
rjson::set_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
rjson::set_with_string_name(deserialized, type_ident, rjson::parse(t.to_string(bytes(bv))));
}
};
rjson::value deserialize_item(bytes_view bv) {
rjson::value deserialized(rapidjson::kObjectType);
if (bv.empty()) {
throw api_error::validation("Serialized value empty");
throw api_error("ValidationException", "Serialized value empty");
}
alternator_type atype = alternator_type(bv[0]);
@@ -140,7 +136,7 @@ rjson::value deserialize_item(bytes_view bv) {
if (atype == alternator_type::NOT_SUPPORTED_YET) {
slogger.trace("Non-optimal deserialization of alternator type {}", int8_t(atype));
return rjson::parse(std::string_view(reinterpret_cast<const char *>(bv.data()), bv.size()));
return rjson::parse_raw(reinterpret_cast<const char *>(bv.data()), bv.size());
}
type_representation type_representation = represent_type(atype);
visit(*type_representation.dtype, to_json_visitor{deserialized, type_representation.ident, bv});
@@ -157,48 +153,34 @@ std::string type_to_string(data_type type) {
};
auto it = types.find(type);
if (it == types.end()) {
// fall back to string, in order to be able to present
// internal Scylla types in a human-readable way
return "S";
throw std::runtime_error(format("Unknown type {}", type->name()));
}
return it->second;
}
bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
std::string column_name = column.name_as_text();
const rjson::value* key_typed_value = rjson::find(item, column_name);
if (!key_typed_value) {
throw api_error::validation(format("Key column {} not found", column_name));
std::string expected_type = type_to_string(column.type);
const rjson::value& key_typed_value = rjson::get(item, rjson::value::StringRefType(column_name.c_str()));
if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1) {
throw api_error("ValidationException",
format("Missing or invalid value object for key column {}: {}", column_name, item));
}
return get_key_from_typed_value(*key_typed_value, column);
return get_key_from_typed_value(key_typed_value, column, expected_type);
}
// Parses the JSON encoding for a key value, which is a map with a single
// entry, whose key is the type (expected to match the key column's type)
// and the value is the encoded value.
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column) {
if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
!key_typed_value.MemberBegin()->value.IsString()) {
throw api_error::validation(
format("Malformed value object for key column {}: {}",
column.name_as_text(), key_typed_value));
}
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type) {
auto it = key_typed_value.MemberBegin();
if (it->name != type_to_string(column.type)) {
throw api_error::validation(
if (it->name.GetString() != expected_type) {
throw api_error("ValidationException",
format("Type mismatch: expected type {} for key column {}, got type {}",
type_to_string(column.type), column.name_as_text(), it->name));
}
std::string_view value_view = rjson::to_string_view(it->value);
if (value_view.empty()) {
throw api_error::validation(
format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
expected_type, column.name_as_text(), it->name.GetString()));
}
if (column.type == bytes_type) {
return base64_decode(it->value);
} else {
return column.type->from_string(rjson::to_string_view(it->value));
return column.type->from_string(it->value.GetString());
}
}
@@ -216,11 +198,8 @@ rjson::value json_key_column_value(bytes_view cell, const column_definition& col
auto s = to_json_string(*decimal_type, bytes(cell));
return rjson::from_string(s);
} else {
// Support for arbitrary key types is useful for parsing values of virtual tables,
// which can involve any type supported by Scylla.
// In order to guarantee that the returned type is parsable by alternator clients,
// they are represented simply as strings.
return rjson::from_string(column.type->to_string(bytes(cell)));
// We shouldn't get here, we shouldn't see such key columns.
throw std::runtime_error(format("Unexpected key type: {}", column.type->name()));
}
}
@@ -251,24 +230,20 @@ clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
if (!v.IsObject() || v.MemberCount() != 1) {
throw api_error::validation(format("{}: invalid number object", diagnostic));
throw api_error("ValidationException", format("{}: invalid number object", diagnostic));
}
auto it = v.MemberBegin();
if (it->name != "N") {
throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
throw api_error("ValidationException", format("{}: expected number, found type '{}'", diagnostic, it->name));
}
try {
if (it->value.IsNumber()) {
// FIXME(sarna): should use big_decimal constructor with numeric values directly:
return big_decimal(rjson::print(it->value));
}
if (!it->value.IsString()) {
throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
}
return big_decimal(rjson::to_string_view(it->value));
} catch (const marshal_exception& e) {
throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", it->value));
if (it->value.IsNumber()) {
// FIXME(sarna): should use big_decimal constructor with numeric values directly:
return big_decimal(rjson::print(it->value));
}
if (!it->value.IsString()) {
throw api_error("ValidationException", format("{}: improperly formatted number constant", diagnostic));
}
return big_decimal(it->value.GetString());
}
const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v) {
@@ -283,93 +258,4 @@ const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value&
return std::make_pair(it_key, &(it->value));
}
const rjson::value* unwrap_list(const rjson::value& v) {
if (!v.IsObject() || v.MemberCount() != 1) {
return nullptr;
}
auto it = v.MemberBegin();
if (it->name != std::string("L")) {
return nullptr;
}
return &(it->value);
}
// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
// sum, again as a JSON-encoded number.
rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
auto n1 = unwrap_number(v1, "UpdateExpression");
auto n2 = unwrap_number(v2, "UpdateExpression");
rjson::value ret = rjson::empty_object();
std::string str_ret = std::string((n1 + n2).to_string());
rjson::set(ret, "N", rjson::from_string(str_ret));
return ret;
}
rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
auto n1 = unwrap_number(v1, "UpdateExpression");
auto n2 = unwrap_number(v2, "UpdateExpression");
rjson::value ret = rjson::empty_object();
std::string str_ret = std::string((n1 - n2).to_string());
rjson::set(ret, "N", rjson::from_string(str_ret));
return ret;
}
// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
// return the sum of both sets, again as a set value.
rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
auto [set1_type, set1] = unwrap_set(v1);
auto [set2_type, set2] = unwrap_set(v2);
if (set1_type != set2_type) {
throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
}
if (!set1 || !set2) {
throw api_error::validation("UpdateExpression: ADD operation for sets must be given sets as arguments");
}
rjson::value sum = rjson::copy(*set1);
std::set<rjson::value, rjson::single_value_comp> set1_raw;
for (auto it = sum.Begin(); it != sum.End(); ++it) {
set1_raw.insert(rjson::copy(*it));
}
for (const auto& a : set2->GetArray()) {
if (!set1_raw.contains(a)) {
rjson::push_back(sum, rjson::copy(a));
}
}
rjson::value ret = rjson::empty_object();
rjson::set_with_string_name(ret, set1_type, std::move(sum));
return ret;
}
// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
// return the difference of s1 - s2, again as a set value.
// DynamoDB does not allow empty sets, so if resulting set is empty, return
// an unset optional instead.
std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2) {
auto [set1_type, set1] = unwrap_set(v1);
auto [set2_type, set2] = unwrap_set(v2);
if (set1_type != set2_type) {
throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
}
if (!set1 || !set2) {
throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");
}
std::set<rjson::value, rjson::single_value_comp> set1_raw;
for (auto it = set1->Begin(); it != set1->End(); ++it) {
set1_raw.insert(rjson::copy(*it));
}
for (const auto& a : set2->GetArray()) {
set1_raw.erase(a);
}
if (set1_raw.empty()) {
return std::nullopt;
}
rjson::value ret = rjson::empty_object();
rjson::set_with_string_name(ret, set1_type, rjson::empty_array());
rjson::value& result_set = ret[set1_type];
for (const auto& a : set1_raw) {
rjson::push_back(result_set, rjson::copy(a));
}
return ret;
}
}

View File

@@ -24,9 +24,9 @@
#include <string>
#include <string_view>
#include "types.hh"
#include "schema_fwd.hh"
#include "schema.hh"
#include "keys.hh"
#include "utils/rjson.hh"
#include "rjson.hh"
#include "utils/big_decimal.hh"
namespace alternator {
@@ -45,7 +45,7 @@ struct type_representation {
data_type dtype;
};
type_info type_info_from_string(std::string_view type);
type_info type_info_from_string(std::string type);
type_representation represent_type(alternator_type atype);
bytes serialize_item(const rjson::value& item);
@@ -54,7 +54,7 @@ rjson::value deserialize_item(bytes_view bv);
std::string type_to_string(data_type type);
bytes get_key_column_value(const rjson::value& item, const column_definition& column);
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column);
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type);
rjson::value json_key_column_value(bytes_view cell, const column_definition& column);
partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
@@ -69,21 +69,4 @@ big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
// returned value is {"", nullptr}
const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v);
// Check if a given JSON object encodes a list (i.e., it is a {"L": [...]}
// and returns a pointer to that list.
const rjson::value* unwrap_list(const rjson::value& v);
// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
// sum, again as a JSON-encoded number.
rjson::value number_add(const rjson::value& v1, const rjson::value& v2);
rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2);
// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
// return the sum of both sets, again as a set value.
rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
// return the difference of s1 - s2, again as a set value.
// DynamoDB does not allow empty sets, so if resulting set is empty, return
// an unset optional instead.
std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2);
}

View File

@@ -23,14 +23,12 @@
#include "log.hh"
#include <seastar/http/function_handlers.hh>
#include <seastar/json/json_elements.hh>
#include "seastarx.hh"
#include <seastarx.hh>
#include "error.hh"
#include "utils/rjson.hh"
#include "rjson.hh"
#include "auth.hh"
#include <cctype>
#include "cql3/query_processor.hh"
#include "service/storage_service.hh"
#include "utils/overloaded_functor.hh"
static logging::logger slogger("alternator-server");
@@ -67,42 +65,41 @@ inline std::vector<std::string_view> split(std::string_view text, char separator
// Internal Server Error.
class api_handler : public handler_base {
public:
api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle) : _f_handle(
[this, _handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped([this, rep = std::move(rep)](future<executor::request_return_type> resf) mutable {
api_handler(const future_json_function& _handle) : _f_handle(
[_handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
return seastar::futurize_apply(_handle, std::move(req)).then_wrapped([rep = std::move(rep)](future<json::json_return_type> resf) mutable {
if (resf.failed()) {
// Exceptions of type api_error are wrapped as JSON and
// returned to the client as expected. Other types of
// exceptions are unexpected, and returned to the user
// as an internal server error:
api_error ret;
try {
resf.get();
} catch (api_error &ae) {
generate_error_reply(*rep, ae);
ret = ae;
} catch (rjson::error & re) {
generate_error_reply(*rep,
api_error::validation(re.what()));
ret = api_error("ValidationException", re.what());
} catch (...) {
generate_error_reply(*rep,
api_error::internal(format("Internal server error: {}", std::current_exception())));
ret = api_error(
"Internal Server Error",
format("Internal server error: {}", std::current_exception()),
reply::status_type::internal_server_error);
}
// FIXME: what is this version number?
rep->_content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + ret._type + "\"," +
"\"message\":\"" + ret._msg + "\"}";
rep->_status = ret._http_code;
slogger.trace("api_handler error case: {}", rep->_content);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
slogger.trace("api_handler success case");
auto res = resf.get0();
std::visit(overloaded_functor {
[&] (const json::json_return_type& json_return_value) {
slogger.trace("api_handler success case");
if (json_return_value._body_writer) {
rep->write_body("json", std::move(json_return_value._body_writer));
} else {
rep->_content += json_return_value._res;
}
},
[&] (const api_error& err) {
generate_error_reply(*rep, err);
}
}, res);
if (res._body_writer) {
rep->write_body("json", std::move(res._body_writer));
} else {
rep->_content += res._res;
}
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
});
}), _type("json") { }
@@ -118,66 +115,18 @@ public:
}
protected:
void generate_error_reply(reply& rep, const api_error& err) {
rep._content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + err._type + "\"," +
"\"message\":\"" + err._msg + "\"}";
rep._status = err._http_code;
slogger.trace("api_handler error case: {}", rep._content);
}
future_handler_function _f_handle;
sstring _type;
};
class gated_handler : public handler_base {
seastar::gate& _gate;
public:
gated_handler(seastar::gate& gate) : _gate(gate) {}
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) = 0;
virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) final override {
return with_gate(_gate, [this, &path, req = std::move(req), rep = std::move(rep)] () mutable {
return do_handle(path, std::move(req), std::move(rep));
});
}
};
class health_handler : public gated_handler {
public:
health_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
protected:
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
class health_handler : public handler_base {
virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
rep->set_status(reply::status_type::ok);
rep->write_body("txt", format("healthy: {}", req->get_header("Host")));
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
};
class local_nodelist_handler : public gated_handler {
public:
local_nodelist_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
protected:
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
rjson::value results = rjson::empty_array();
// It's very easy to get a list of all live nodes on the cluster,
// using gms::get_local_gossiper().get_live_members(). But getting
// just the list of live nodes in this DC needs more elaborate code:
sstring local_dc = locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(
utils::fb_utilities::get_broadcast_address());
std::unordered_set<gms::inet_address> local_dc_nodes =
service::get_local_storage_service().get_token_metadata().
get_topology().get_datacenter_endpoints().at(local_dc);
for (auto& ip : local_dc_nodes) {
if (gms::get_local_gossiper().is_alive(ip)) {
rjson::push_back(results, rjson::from_string(ip.to_sstring()));
}
}
rep->set_status(reply::status_type::ok);
rep->set_content_type("json");
rep->_content = rjson::print(results);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
};
future<> server::verify_signature(const request& req) {
if (!_enforce_authorization) {
slogger.debug("Skipping authorization");
@@ -185,11 +134,11 @@ future<> server::verify_signature(const request& req) {
}
auto host_it = req._headers.find("Host");
if (host_it == req._headers.end()) {
throw api_error::invalid_signature("Host header is mandatory for signature verification");
throw api_error("InvalidSignatureException", "Host header is mandatory for signature verification");
}
auto authorization_it = req._headers.find("Authorization");
if (authorization_it == req._headers.end()) {
throw api_error::invalid_signature("Authorization header is mandatory for signature verification");
if (host_it == req._headers.end()) {
throw api_error("InvalidSignatureException", "Authorization header is mandatory for signature verification");
}
std::string host = host_it->second;
std::vector<std::string_view> credentials_raw = split(authorization_it->second, ' ');
@@ -201,7 +150,7 @@ future<> server::verify_signature(const request& req) {
std::vector<std::string_view> entry_split = split(entry, '=');
if (entry_split.size() != 2) {
if (entry != "AWS4-HMAC-SHA256") {
throw api_error::invalid_signature(format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
throw api_error("InvalidSignatureException", format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
}
continue;
}
@@ -222,7 +171,7 @@ future<> server::verify_signature(const request& req) {
}
std::vector<std::string_view> credential_split = split(credential, '/');
if (credential_split.size() != 5) {
throw api_error::validation(format("Incorrect credential information format: {}", credential));
throw api_error("ValidationException", format("Incorrect credential information format: {}", credential));
}
std::string user(credential_split[0]);
std::string datestamp(credential_split[1]);
@@ -243,8 +192,8 @@ future<> server::verify_signature(const request& req) {
}
}
auto cache_getter = [&qp = _qp] (std::string username) {
return get_key_from_roles(qp, std::move(username));
auto cache_getter = [] (std::string username) {
return get_key_from_roles(cql3::get_query_processor().local(), std::move(username));
};
return _key_cache.get_ptr(user, cache_getter).then([this, &req,
user = std::move(user),
@@ -260,46 +209,32 @@ future<> server::verify_signature(const request& req) {
if (signature != std::string_view(user_signature)) {
_key_cache.remove(user);
throw api_error::unrecognized_client("The security token included in the request is invalid.");
throw api_error("UnrecognizedClientException", "The security token included in the request is invalid.");
}
});
}
future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
_executor._stats.total_operations++;
future<json::json_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
_executor.local()._stats.total_operations++;
sstring target = req->get_header(TARGET);
std::vector<std::string_view> split_target = split(target, '.');
//NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
slogger.trace("Request: {} {} {}", op, req->content, req->_headers);
slogger.trace("Request: {} {}", op, req->content);
return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
auto callback_it = _callbacks.find(op);
if (callback_it == _callbacks.end()) {
_executor._stats.unsupported_operations++;
throw api_error::unknown_operation(format("Unsupported operation {}", op));
_executor.local()._stats.unsupported_operations++;
throw api_error("UnknownOperationException",
format("Unsupported operation {}", op));
}
return with_gate(_pending_requests, [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] () mutable {
//FIXME: Client state can provide more context, e.g. client's endpoint address
// We use unique_ptr because client_state cannot be moved or copied
return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()),
[this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
tracing::trace(trace_state, op);
// JSON parsing can allocate up to roughly 2x the size of the raw document, + a couple of bytes for maintenance.
// FIXME: by this time, the whole HTTP request was already read, so some memory is already occupied.
// Once HTTP allows working on streams, we should grab the permit *before* reading the HTTP payload.
size_t mem_estimate = req->content.size() * 3 + 8000;
auto units_fut = get_units(*_memory_limiter, mem_estimate);
if (_memory_limiter->waiters()) {
++_executor._stats.requests_blocked_memory;
}
return units_fut.then([this, callback_it = std::move(callback_it), &client_state, trace_state, req = std::move(req)] (semaphore_units<> units) mutable {
return _json_parser.parse(req->content).then([this, callback_it = std::move(callback_it), &client_state, trace_state,
units = std::move(units), req = std::move(req)] (rjson::value json_request) mutable {
return callback_it->second(_executor, *client_state, trace_state, make_service_permit(std::move(units)), std::move(json_request), std::move(req)).finally([trace_state] {});
});
});
});
//FIXME: Client state can provide more context, e.g. client's endpoint address
// We use unique_ptr because client_state cannot be moved or copied
return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()), [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
client_state->set_raw_keyspace(executor::KEYSPACE_NAME);
tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
tracing::trace(trace_state, op);
return callback_it->second(_executor.local(), *client_state, trace_state, std::move(req)).finally([trace_state] {});
});
});
}
@@ -309,104 +244,35 @@ void server::set_routes(routes& r) {
return handle_api_request(std::move(req));
});
r.put(operation_type::POST, "/", req_handler);
r.put(operation_type::GET, "/", new health_handler(_pending_requests));
// The "/localnodes" request is a new Alternator feature, not supported by
// DynamoDB and not required for DynamoDB compatibility. It allows a
// client to enquire - using a trivial HTTP request without requiring
// authentication - the list of all live nodes in the same data center of
// the Alternator cluster. The client can use this list to balance its
// request load to all the nodes in the same geographical region.
// Note that this API exposes - openly without authentication - the
// information on the cluster's members inside one data center. We do not
// consider this to be a security risk, because an attacker can already
// scan an entire subnet for nodes responding to the health request,
// or even just scan for open ports.
r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests));
r.add(operation_type::POST, url("/"), req_handler);
r.add(operation_type::GET, url("/"), new health_handler);
}
//FIXME: A way to immediately invalidate the cache should be considered,
// e.g. when the system table which stores the keys is changed.
// For now, this propagation may take up to 1 minute.
server::server(executor& exec, cql3::query_processor& qp)
: _http_server("http-alternator")
, _https_server("https-alternator")
, _executor(exec)
, _qp(qp)
, _key_cache(1024, 1min, slogger)
, _enforce_authorization(false)
, _enabled_servers{}
, _pending_requests{}
server::server(seastar::sharded<executor>& e)
: _executor(e), _key_cache(1024, 1min, slogger), _enforce_authorization(false)
, _callbacks{
{"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.create_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DescribeTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.describe_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DeleteTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.delete_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"UpdateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.update_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"PutItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.put_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"UpdateItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.update_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"GetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DeleteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.delete_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"ListTables", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.list_tables(client_state, std::move(permit), std::move(json_request));
}},
{"Scan", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.scan(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.describe_endpoints(client_state, std::move(permit), std::move(json_request), req->get_header("Host"));
}},
{"BatchWriteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.batch_write_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"BatchGetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.batch_get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"Query", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.query(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"TagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.tag_resource(client_state, std::move(permit), std::move(json_request));
}},
{"UntagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.untag_resource(client_state, std::move(permit), std::move(json_request));
}},
{"ListTagsOfResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.list_tags_of_resource(client_state, std::move(permit), std::move(json_request));
}},
{"ListStreams", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.list_streams(client_state, std::move(permit), std::move(json_request));
}},
{"DescribeStream", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.describe_stream(client_state, std::move(permit), std::move(json_request));
}},
{"GetShardIterator", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.get_shard_iterator(client_state, std::move(permit), std::move(json_request));
}},
{"GetRecords", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.get_records(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) {
return e.maybe_create_keyspace().then([&e, &client_state, req = std::move(req), trace_state = std::move(trace_state)] () mutable { return e.create_table(client_state, std::move(trace_state), req->content); }); }
},
{"DescribeTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.describe_table(client_state, std::move(trace_state), req->content); }},
{"DeleteTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.delete_table(client_state, std::move(trace_state), req->content); }},
{"PutItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.put_item(client_state, std::move(trace_state), req->content); }},
{"UpdateItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.update_item(client_state, std::move(trace_state), req->content); }},
{"GetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.get_item(client_state, std::move(trace_state), req->content); }},
{"DeleteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.delete_item(client_state, std::move(trace_state), req->content); }},
{"ListTables", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.list_tables(client_state, req->content); }},
{"Scan", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.scan(client_state, std::move(trace_state), req->content); }},
{"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.describe_endpoints(client_state, req->content, req->get_header("Host")); }},
{"BatchWriteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.batch_write_item(client_state, std::move(trace_state), req->content); }},
{"BatchGetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.batch_get_item(client_state, std::move(trace_state), req->content); }},
{"Query", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, std::unique_ptr<request> req) { return e.query(client_state, std::move(trace_state), req->content); }},
} {
}
future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
bool enforce_authorization, semaphore* memory_limiter) {
_memory_limiter = memory_limiter;
future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds, bool enforce_authorization) {
_enforce_authorization = enforce_authorization;
if (!port && !https_port) {
return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
@@ -414,26 +280,25 @@ future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std:
}
return seastar::async([this, addr, port, https_port, creds] {
try {
_executor.start().get();
_executor.invoke_on_all([] (executor& e) {
return e.start();
}).get();
if (port) {
set_routes(_http_server._routes);
_http_server.set_content_length_limit(server::content_length_limit);
_http_server.listen(socket_address{addr, *port}).get();
_enabled_servers.push_back(std::ref(_http_server));
_control.start().get();
_control.set_routes(std::bind(&server::set_routes, this, std::placeholders::_1)).get();
_control.listen(socket_address{addr, *port}).get();
slogger.info("Alternator HTTP server listening on {} port {}", addr, *port);
}
if (https_port) {
set_routes(_https_server._routes);
_https_server.set_content_length_limit(server::content_length_limit);
_https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
if (ep) {
slogger.warn("Exception loading {}: {}", files, ep);
} else {
slogger.info("Reloaded {}", files);
}
}).get0());
_https_server.listen(socket_address{addr, *https_port}).get();
_enabled_servers.push_back(std::ref(_https_server));
_https_control.start().get();
_https_control.set_routes(std::bind(&server::set_routes, this, std::placeholders::_1)).get();
_https_control.server().invoke_on_all([creds] (http_server& serv) {
return serv.set_tls_credentials(creds->build_server_credentials());
}).get();
_https_control.listen(socket_address{addr, *https_port}).get();
slogger.info("Alternator HTTPS server listening on {} port {}", addr, *https_port);
}
} catch (...) {
slogger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
@@ -445,55 +310,5 @@ future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std:
});
}
future<> server::stop() {
return parallel_for_each(_enabled_servers, [] (http_server& server) {
return server.stop();
}).then([this] {
return _pending_requests.close();
}).then([this] {
return _json_parser.stop();
});
}
server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
while (true) {
_document_waiting.wait().get();
if (_as.abort_requested()) {
return;
}
try {
_parsed_document = rjson::parse_yieldable(_raw_document);
_current_exception = nullptr;
} catch (...) {
_current_exception = std::current_exception();
}
_document_parsed.signal();
}
})) {
}
future<rjson::value> server::json_parser::parse(std::string_view content) {
if (content.size() < yieldable_parsing_threshold) {
return make_ready_future<rjson::value>(rjson::parse(content));
}
return with_semaphore(_parsing_sem, 1, [this, content] {
_raw_document = content;
_document_waiting.signal();
return _document_parsed.wait().then([this] {
if (_current_exception) {
return make_exception_future<rjson::value>(_current_exception);
}
return make_ready_future<rjson::value>(std::move(_parsed_document));
});
});
}
future<> server::json_parser::stop() {
_as.request_abort();
_document_waiting.signal();
_document_parsed.broken();
return std::move(_run_parse_json_thread);
}
}

View File

@@ -26,58 +26,28 @@
#include <seastar/http/httpd.hh>
#include <seastar/net/tls.hh>
#include <optional>
#include "alternator/auth.hh"
#include "utils/small_vector.hh"
#include <seastar/core/units.hh>
#include <alternator/auth.hh>
namespace alternator {
class server {
static constexpr size_t content_length_limit = 16*MB;
using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
using alternator_callback = std::function<future<json::json_return_type>(executor&, executor::client_state&, tracing::trace_state_ptr, std::unique_ptr<request>)>;
using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
http_server _http_server;
http_server _https_server;
executor& _executor;
cql3::query_processor& _qp;
seastar::httpd::http_server_control _control;
seastar::httpd::http_server_control _https_control;
seastar::sharded<executor>& _executor;
key_cache _key_cache;
bool _enforce_authorization;
utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
gate _pending_requests;
alternator_callbacks_map _callbacks;
semaphore* _memory_limiter;
class json_parser {
static constexpr size_t yieldable_parsing_threshold = 16*KB;
std::string_view _raw_document;
rjson::value _parsed_document;
std::exception_ptr _current_exception;
semaphore _parsing_sem{1};
condition_variable _document_waiting;
condition_variable _document_parsed;
abort_source _as;
future<> _run_parse_json_thread;
public:
json_parser();
future<rjson::value> parse(std::string_view content);
future<> stop();
};
json_parser _json_parser;
public:
server(executor& executor, cql3::query_processor& qp);
server(seastar::sharded<executor>& executor);
future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
bool enforce_authorization, semaphore* memory_limiter);
future<> stop();
seastar::future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds, bool enforce_authorization);
private:
void set_routes(seastar::httpd::routes& r);
future<> verify_signature(const seastar::httpd::request& r);
future<executor::request_return_type> handle_api_request(std::unique_ptr<request>&& req);
future<json::json_return_type> handle_api_request(std::unique_ptr<request>&& req);
};
}

View File

@@ -20,7 +20,7 @@
*/
#include "stats.hh"
#include "utils/histogram_metrics_helper.hh"
#include <seastar/core/metrics.hh>
namespace alternator {
@@ -37,7 +37,7 @@ stats::stats() : api_operations{} {
seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
#define OPERATION_LATENCY(name, CamelCaseName) \
seastar::metrics::make_histogram("op_latency", \
seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return to_metrics_histogram(api_operations.name);}),
seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return api_operations.name.get_histogram(1,20);}),
OPERATION(batch_write_item, "BatchWriteItem")
OPERATION(create_backup, "CreateBackup")
OPERATION(create_global_table, "CreateGlobalTable")
@@ -77,11 +77,6 @@ stats::stats() : api_operations{} {
OPERATION_LATENCY(get_item_latency, "GetItem")
OPERATION_LATENCY(delete_item_latency, "DeleteItem")
OPERATION_LATENCY(update_item_latency, "UpdateItem")
OPERATION(list_streams, "ListStreams")
OPERATION(describe_stream, "DescribeStream")
OPERATION(get_shard_iterator, "GetShardIterator")
OPERATION(get_records, "GetRecords")
OPERATION_LATENCY(get_records_latency, "GetRecords")
});
_metrics.add_group("alternator", {
seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
@@ -90,12 +85,6 @@ stats::stats() : api_operations{} {
seastar::metrics::description("number of total operations via Alternator API")),
seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
seastar::metrics::description("number of performed read-before-write operations")),
seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
seastar::metrics::description("number of writes that used LWT")),
seastar::metrics::make_total_operations("shard_bounce_for_lwt", shard_bounce_for_lwt,
seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
seastar::metrics::description("number of rows read during filtering operations")),
seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,

View File

@@ -74,24 +74,16 @@ public:
uint64_t update_item = 0;
uint64_t update_table = 0;
uint64_t update_time_to_live = 0;
uint64_t list_streams = 0;
uint64_t describe_stream = 0;
uint64_t get_shard_iterator = 0;
uint64_t get_records = 0;
utils::time_estimated_histogram put_item_latency;
utils::time_estimated_histogram get_item_latency;
utils::time_estimated_histogram delete_item_latency;
utils::time_estimated_histogram update_item_latency;
utils::time_estimated_histogram get_records_latency;
utils::estimated_histogram put_item_latency;
utils::estimated_histogram get_item_latency;
utils::estimated_histogram delete_item_latency;
utils::estimated_histogram update_item_latency;
} api_operations;
// Miscellaneous event counters
uint64_t total_operations = 0;
uint64_t unsupported_operations = 0;
uint64_t reads_before_write = 0;
uint64_t write_using_lwt = 0;
uint64_t shard_bounce_for_lwt = 0;
uint64_t requests_blocked_memory = 0;
// CQL-derived stats
cql3::cql_stats cql_stats;
private:

File diff suppressed because it is too large Load Diff

View File

@@ -1,53 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "serializer.hh"
#include "schema.hh"
#include "db/extensions.hh"
namespace alternator {
class tags_extension : public schema_extension {
public:
static constexpr auto NAME = "scylla_tags";
tags_extension() = default;
explicit tags_extension(const std::map<sstring, sstring>& tags) : _tags(std::move(tags)) {}
explicit tags_extension(bytes b) : _tags(tags_extension::deserialize(b)) {}
explicit tags_extension(const sstring& s) {
throw std::logic_error("Cannot create tags from string");
}
bytes serialize() const override {
return ser::serialize_to_buffer<bytes>(_tags);
}
static std::map<sstring, sstring> deserialize(bytes_view buffer) {
return ser::deserialize_from_buffer(buffer, boost::type<std::map<sstring, sstring>>());
}
const std::map<sstring, sstring>& tags() const {
return _tags;
}
private:
std::map<sstring, sstring> _tags;
};
}

View File

@@ -70,7 +70,7 @@
{
"method":"POST",
"summary":"Force a major compaction of this column family",
"type":"void",
"type":"string",
"nickname":"force_major_compaction",
"produces":[
"application/json"
@@ -380,54 +380,16 @@
"operations":[
{
"method":"GET",
"summary":"check if the auto_compaction property is enabled for a given table",
"summary":"check if the auto compaction disabled",
"type":"boolean",
"nickname":"get_auto_compaction",
"nickname":"is_auto_compaction_disabled",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
},
{
"method":"POST",
"summary":"Enable table auto compaction",
"type":"void",
"nickname":"enable_auto_compaction",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
},
{
"method":"DELETE",
"summary":"Disable table auto compaction",
"type":"void",
"nickname":"disable_auto_compaction",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",

View File

@@ -1,90 +0,0 @@
{
"apiVersion":"0.0.1",
"swaggerVersion":"1.2",
"basePath":"{{Protocol}}://{{Host}}",
"resourcePath":"/error_injection",
"produces":[
"application/json"
],
"apis":[
{
"path":"/v2/error_injection/injection/{injection}",
"operations":[
{
"method":"POST",
"summary":"Activate an injection that triggers an error in code",
"type":"void",
"nickname":"enable_injection",
"produces":[
"application/json"
],
"parameters":[
{
"name":"injection",
"description":"injection name, should correspond to an injection added in code",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"one_shot",
"description":"boolean flag indicating whether the injection should be enabled to trigger only once",
"required":false,
"allowMultiple":false,
"type":"boolean",
"paramType":"query"
}
]
},
{
"method":"DELETE",
"summary":"Deactivate an injection previously activated by the API",
"type":"void",
"nickname":"disable_injection",
"produces":[
"application/json"
],
"parameters":[
{
"name":"injection",
"description":"injection name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
},
{
"path":"/v2/error_injection/injection",
"operations":[
{
"method":"GET",
"summary":"List all enabled injections on all shards, i.e. injections that will trigger an error in the code",
"type":"array",
"items":{
"type":"string"
},
"nickname":"get_enabled_injections_on_all",
"produces":[
"application/json"
],
"parameters":[]
},
{
"method":"DELETE",
"summary":"Deactivate all injections previously activated on all shards by the API",
"type":"void",
"nickname":"disable_on_all",
"produces":[
"application/json"
],
"parameters":[]
}
]
}
]
}

View File

@@ -249,7 +249,7 @@
"MIGRATION_REQUEST",
"PREPARE_MESSAGE",
"PREPARE_DONE_MESSAGE",
"UNUSED__STREAM_MUTATION",
"STREAM_MUTATION",
"STREAM_MUTATION_DONE",
"COMPLETE_MESSAGE",
"REPAIR_CHECKSUM_RANGE",

View File

@@ -68,7 +68,7 @@
"summary":"Get the hinted handoff enabled by dc",
"type":"array",
"items":{
"type":"array"
"type":"mapper_list"
},
"nickname":"get_hinted_handoff_enabled_by_dc",
"produces":[
@@ -641,21 +641,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/cas_write/failed_read_round_optimization",
"operations": [
{
"method": "GET",
"summary": "Get cas write metrics",
"type": "long",
"nickname": "get_cas_write_metrics_failed_read_round_optimization",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/cas_read/unfinished_commit",
"operations": [

View File

@@ -511,21 +511,6 @@
}
]
},
{
"path":"/storage_service/cdc_streams_check_and_repair",
"operations":[
{
"method":"POST",
"summary":"Checks that CDC streams reflect current cluster topology and regenerates them if not.",
"type":"void",
"nickname":"cdc_streams_check_and_repair",
"produces":[
"application/json"
],
"parameters":[]
}
]
},
{
"path":"/storage_service/snapshots",
"operations":[
@@ -597,15 +582,7 @@
},
{
"name":"kn",
"description":"Comma seperated keyspaces name that their snapshot will be deleted",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"cf",
"description":"an optional table name that its snapshot will be deleted",
"description":"Comma seperated keyspaces name to snapshot",
"required":false,
"allowMultiple":false,
"type":"string",
@@ -833,43 +810,6 @@
}
]
},
{
"path":"/storage_service/repair_status/",
"operations":[
{
"method":"GET",
"summary":"Query the repair status and return when the repair is finished or timeout",
"type":"string",
"enum":[
"RUNNING",
"SUCCESSFUL",
"FAILED"
],
"nickname":"repair_await_completion",
"produces":[
"application/json"
],
"parameters":[
{
"name":"id",
"description":"The repair ID to check for status",
"required":true,
"allowMultiple":false,
"type": "long",
"paramType":"query"
},
{
"name":"timeout",
"description":"Seconds to wait before the query returns even if the repair is not finished. The value -1 or not providing this parameter means no timeout",
"required":false,
"allowMultiple":false,
"type": "long",
"paramType":"query"
}
]
}
]
},
{
"path":"/storage_service/repair_async/{keyspace}",
"operations":[
@@ -2468,7 +2408,7 @@
"version":{
"type":"string",
"enum":[
"ka", "la", "mc", "md"
"ka", "la", "mc"
],
"description":"SSTable version"
},

View File

@@ -36,7 +36,6 @@
#include "endpoint_snitch.hh"
#include "compaction_manager.hh"
#include "hinted_handoff.hh"
#include "error_injection.hh"
#include <seastar/http/exception.hh>
#include "stream_manager.hh"
#include "system.hh"
@@ -69,19 +68,13 @@ future<> set_server_init(http_context& ctx) {
rb->set_api_doc(r);
rb02->set_api_doc(r);
rb02->register_api_file(r, "swagger20_header");
set_config(rb02, ctx, r);
rb->register_function(r, "system",
"The system related API");
set_system(ctx, r);
});
}
future<> set_server_config(http_context& ctx) {
auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
set_config(rb02, ctx, r);
});
}
static future<> register_api(http_context& ctx, const sstring& api_name,
const sstring api_desc,
std::function<void(http_context& ctx, routes& r)> f) {
@@ -93,42 +86,10 @@ static future<> register_api(http_context& ctx, const sstring& api_name,
});
}
future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl) {
return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_transport_controller(ctx, r, ctl); });
}
future<> unset_transport_controller(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_transport_controller(ctx, r); });
}
future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl) {
return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_rpc_controller(ctx, r, ctl); });
}
future<> unset_rpc_controller(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_rpc_controller(ctx, r); });
}
future<> set_server_storage_service(http_context& ctx) {
return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
}
future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms) {
return ctx.http_server.set_routes([&ctx, &ms] (routes& r) { set_repair(ctx, r, ms); });
}
future<> unset_server_repair(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_repair(ctx, r); });
}
future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl) {
return ctx.http_server.set_routes([&ctx, &snap_ctl] (routes& r) { set_snapshot(ctx, r, snap_ctl); });
}
future<> unset_server_snapshot(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_snapshot(ctx, r); });
}
future<> set_server_snitch(http_context& ctx) {
return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
}
@@ -143,14 +104,9 @@ future<> set_server_load_sstable(http_context& ctx) {
"The column family API", set_column_family);
}
future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms) {
future<> set_server_messaging_service(http_context& ctx) {
return register_api(ctx, "messaging_service",
"The messaging service API", [&ms] (http_context& ctx, routes& r) {
set_messaging_service(ctx, r, ms);
});
}
future<> unset_server_messaging_service(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_messaging_service(ctx, r); });
"The messaging service API", set_messaging_service);
}
future<> set_server_storage_proxy(http_context& ctx) {
@@ -197,9 +153,6 @@ future<> set_server_done(http_context& ctx) {
rb->register_function(r, "collectd",
"The collectd API");
set_collectd(ctx, r);
rb->register_function(r, "error_injection",
"The error injection API");
set_error_injection(ctx, r);
});
}

View File

@@ -256,6 +256,4 @@ public:
operator T() const { return value; }
};
utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val);
}

View File

@@ -24,11 +24,6 @@
#include <seastar/http/httpd.hh>
namespace service { class load_meter; }
namespace locator { class shared_token_metadata; }
namespace cql_transport { class controller; }
class thrift_controller;
namespace db { class snapshot_ctl; }
namespace netw { class messaging_service; }
namespace api {
@@ -39,33 +34,19 @@ struct http_context {
distributed<database>& db;
distributed<service::storage_proxy>& sp;
service::load_meter& lmeter;
const sharded<locator::shared_token_metadata>& shared_token_metadata;
http_context(distributed<database>& _db,
distributed<service::storage_proxy>& _sp,
service::load_meter& _lm, const sharded<locator::shared_token_metadata>& _stm)
: db(_db), sp(_sp), lmeter(_lm), shared_token_metadata(_stm) {
service::load_meter& _lm)
: db(_db), sp(_sp), lmeter(_lm) {
}
const locator::token_metadata& get_token_metadata();
};
future<> set_server_init(http_context& ctx);
future<> set_server_config(http_context& ctx);
future<> set_server_snitch(http_context& ctx);
future<> set_server_storage_service(http_context& ctx);
future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms);
future<> unset_server_repair(http_context& ctx);
future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
future<> unset_transport_controller(http_context& ctx);
future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
future<> unset_rpc_controller(http_context& ctx);
future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
future<> unset_server_snapshot(http_context& ctx);
future<> set_server_gossip(http_context& ctx);
future<> set_server_load_sstable(http_context& ctx);
future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms);
future<> unset_server_messaging_service(http_context& ctx);
future<> set_server_messaging_service(http_context& ctx);
future<> set_server_storage_proxy(http_context& ctx);
future<> set_server_stream_manager(http_context& ctx);
future<> set_server_gossip_settle(http_context& ctx);

View File

@@ -208,11 +208,9 @@ void set_cache_service(http_context& ctx, routes& r) {
});
cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().region().occupancy().used_space();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
return cf.get_row_cache().get_cache_tracker().region().occupancy().used_space();
}, std::plus<uint64_t>());
});
cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -253,19 +251,15 @@ void set_cache_service(http_context& ctx, routes& r) {
cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// In origin row size is the weighted size.
// We currently do not support weights, so we use num entries instead
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().partitions();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
}, std::plus<uint64_t>());
});
cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().partitions();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
}, std::plus<uint64_t>());
});
cs::get_counter_capacity.set(r, [] (std::unique_ptr<request> req) {

View File

@@ -64,7 +64,7 @@ static const char* str_to_regex(const sstring& v) {
void set_collectd(http_context& ctx, routes& r) {
cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
auto id = ::make_shared<scollectd::type_instance_id>(req->param["pluginid"],
auto id = make_shared<scollectd::type_instance_id>(req->param["pluginid"],
req->get_query_param("instance"), req->get_query_param("type"),
req->get_query_param("type_instance"));

View File

@@ -249,12 +249,6 @@ static future<json::json_return_type> sum_sstable(http_context& ctx, bool total)
});
}
future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f) {
return map_reduce_cf_raw(ctx, name, utils::time_estimated_histogram(), f, utils::time_estimated_histogram_merge).then([](const utils::time_estimated_histogram& res) {
return make_ready_future<json::json_return_type>(time_to_json_histogram(res));
});
}
template <typename T>
class sum_ratio {
uint64_t _n = 0;
@@ -802,21 +796,24 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_cas_prepare.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_prepare;
});
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
cf::get_cas_propose.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
return cf.get_stats().estimated_cas_accept;
});
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_propose;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
cf::get_cas_commit.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
return cf.get_stats().estimated_cas_learn;
});
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_commit;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -842,32 +839,15 @@ void set_column_family(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(res);
});
cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
const utils::UUID& uuid = get_uuid(req.param["name"], ctx.db.local());
column_family& cf = ctx.db.local().find_column_family(uuid);
return !cf.is_auto_compaction_disabled_by_user();
});
cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
cf.enable_auto_compaction();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
cf.disable_auto_compaction();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
cf::is_auto_compaction_disabled.set(r, [] (const_req req) {
// FIXME
// currently auto compaction is disable
// it should be changed when it would have an API
return true;
});
cf::get_built_indexes.set(r, [&ctx](std::unique_ptr<request> req) {
auto ks_cf = parse_fully_qualified_cf_name(req->param["name"]);
auto&& ks = std::get<0>(ks_cf);
auto&& cf_name = std::get<1>(ks_cf);
auto [ks, cf_name] = parse_fully_qualified_cf_name(req->param["name"]);
return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_build_progress>& vb) mutable {
std::set<sstring> vp;
for (auto b : vb) {
@@ -880,7 +860,7 @@ void set_column_family(http_context& ctx, routes& r) {
column_family& cf = ctx.db.local().find_column_family(uuid);
res.reserve(cf.get_index_manager().list_indexes().size());
for (auto&& i : cf.get_index_manager().list_indexes()) {
if (!vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
if (vp.find(secondary_index::index_table_name(i.metadata().name())) == vp.end()) {
res.emplace_back(i.metadata().name());
}
}
@@ -914,15 +894,17 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_read_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_read;
});
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
cf::get_write_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_write;
});
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -1012,15 +994,5 @@ void set_column_family(http_context& ctx, routes& r) {
});
});
cf::force_major_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
if (req->get_query_param("split_output") != "") {
fail(unimplemented::cause::API);
}
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
return cf.compact_all_sstables();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
}
}

View File

@@ -68,8 +68,6 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
});
}
future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f);
struct map_reduce_column_families_locally {
std::any init;
std::function<std::unique_ptr<std::any>(column_family&)> mapper;

View File

@@ -20,7 +20,7 @@
*/
#include "commitlog.hh"
#include "db/commitlog/commitlog.hh"
#include <db/commitlog/commitlog.hh>
#include "api/api-doc/commitlog.json.hh"
#include "database.hh"
#include <vector>

View File

@@ -1,69 +0,0 @@
/*
* Copyright (C) 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "api/api-doc/error_injection.json.hh"
#include "api/api.hh"
#include <seastar/http/exception.hh>
#include "log.hh"
#include "utils/error_injection.hh"
#include "seastar/core/future-util.hh"
namespace api {
namespace hf = httpd::error_injection_json;
void set_error_injection(http_context& ctx, routes& r) {
hf::enable_injection.set(r, [](std::unique_ptr<request> req) {
sstring injection = req->param["injection"];
bool one_shot = req->get_query_param("one_shot") == "True";
auto& errinj = utils::get_local_injector();
return errinj.enable_on_all(injection, one_shot).then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
hf::get_enabled_injections_on_all.set(r, [](std::unique_ptr<request> req) {
auto& errinj = utils::get_local_injector();
auto ret = errinj.enabled_injections_on_all();
return make_ready_future<json::json_return_type>(ret);
});
hf::disable_injection.set(r, [](std::unique_ptr<request> req) {
sstring injection = req->param["injection"];
auto& errinj = utils::get_local_injector();
return errinj.disable_on_all(injection).then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
hf::disable_on_all.set(r, [](std::unique_ptr<request> req) {
auto& errinj = utils::get_local_injector();
return errinj.disable_on_all().then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
}
} // namespace api

View File

@@ -1,30 +0,0 @@
/*
* Copyright (C) 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "api.hh"
namespace api {
void set_error_injection(http_context& ctx, routes& r);
}

View File

@@ -21,7 +21,7 @@
#include "gossiper.hh"
#include "api/api-doc/gossiper.json.hh"
#include "gms/gossiper.hh"
#include <gms/gossiper.hh>
namespace api {
using namespace json;

View File

@@ -53,8 +53,8 @@ std::vector<message_counter> map_to_message_counters(
* according to a function that it gets as a parameter.
*
*/
future_json_function get_client_getter(sharded<netw::messaging_service>& ms, std::function<uint64_t(const shard_info&)> f) {
return [&ms, f](std::unique_ptr<request> req) {
future_json_function get_client_getter(std::function<uint64_t(const shard_info&)> f) {
return [f](std::unique_ptr<request> req) {
using map_type = std::unordered_map<gms::inet_address, uint64_t>;
auto get_shard_map = [f](messaging_service& ms) {
std::unordered_map<gms::inet_address, unsigned long> map;
@@ -63,15 +63,15 @@ future_json_function get_client_getter(sharded<netw::messaging_service>& ms, std
});
return map;
};
return ms.map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
return get_messaging_service().map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
then([](map_type&& map) {
return make_ready_future<json::json_return_type>(map_to_message_counters(map));
});
};
}
future_json_function get_server_getter(sharded<netw::messaging_service>& ms, std::function<uint64_t(const rpc::stats&)> f) {
return [&ms, f](std::unique_ptr<request> req) {
future_json_function get_server_getter(std::function<uint64_t(const rpc::stats&)> f) {
return [f](std::unique_ptr<request> req) {
using map_type = std::unordered_map<gms::inet_address, uint64_t>;
auto get_shard_map = [f](messaging_service& ms) {
std::unordered_map<gms::inet_address, unsigned long> map;
@@ -80,53 +80,53 @@ future_json_function get_server_getter(sharded<netw::messaging_service>& ms, std
});
return map;
};
return ms.map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
return get_messaging_service().map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
then([](map_type&& map) {
return make_ready_future<json::json_return_type>(map_to_message_counters(map));
});
};
}
void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms) {
get_timeout_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
void set_messaging_service(http_context& ctx, routes& r) {
get_timeout_messages.set(r, get_client_getter([](const shard_info& c) {
return c.get_stats().timeout;
}));
get_sent_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
get_sent_messages.set(r, get_client_getter([](const shard_info& c) {
return c.get_stats().sent_messages;
}));
get_dropped_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
get_dropped_messages.set(r, get_client_getter([](const shard_info& c) {
// We don't have the same drop message mechanism
// as origin has.
// hence we can always return 0
return 0;
}));
get_exception_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
get_exception_messages.set(r, get_client_getter([](const shard_info& c) {
return c.get_stats().exception_received;
}));
get_pending_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
get_pending_messages.set(r, get_client_getter([](const shard_info& c) {
return c.get_stats().pending;
}));
get_respond_pending_messages.set(r, get_server_getter(ms, [](const rpc::stats& c) {
get_respond_pending_messages.set(r, get_server_getter([](const rpc::stats& c) {
return c.pending;
}));
get_respond_completed_messages.set(r, get_server_getter(ms, [](const rpc::stats& c) {
get_respond_completed_messages.set(r, get_server_getter([](const rpc::stats& c) {
return c.sent_messages;
}));
get_version.set(r, [&ms](const_req req) {
return ms.local().get_raw_version(req.get_query_param("addr"));
get_version.set(r, [](const_req req) {
return netw::get_local_messaging_service().get_raw_version(req.get_query_param("addr"));
});
get_dropped_messages_by_ver.set(r, [&ms](std::unique_ptr<request> req) {
get_dropped_messages_by_ver.set(r, [](std::unique_ptr<request> req) {
shared_ptr<std::vector<uint64_t>> map = make_shared<std::vector<uint64_t>>(num_verb);
return ms.map_reduce([map](const uint64_t* local_map) mutable {
return netw::get_messaging_service().map_reduce([map](const uint64_t* local_map) mutable {
for (auto i = 0; i < num_verb; i++) {
(*map)[i]+= local_map[i];
}
@@ -151,18 +151,5 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
});
});
}
void unset_messaging_service(http_context& ctx, routes& r) {
get_timeout_messages.unset(r);
get_sent_messages.unset(r);
get_dropped_messages.unset(r);
get_exception_messages.unset(r);
get_pending_messages.unset(r);
get_respond_pending_messages.unset(r);
get_respond_completed_messages.unset(r);
get_version.unset(r);
get_dropped_messages_by_ver.unset(r);
}
}

View File

@@ -23,11 +23,8 @@
#include "api.hh"
namespace netw { class messaging_service; }
namespace api {
void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
void unset_messaging_service(http_context& ctx, routes& r);
void set_messaging_service(http_context& ctx, routes& r);
}

View File

@@ -27,7 +27,6 @@
#include "db/config.hh"
#include "utils/histogram.hh"
#include "database.hh"
#include "seastar/core/scheduling_specific.hh"
namespace api {
@@ -35,70 +34,12 @@ namespace sp = httpd::storage_proxy_json;
using proxy = service::storage_proxy;
using namespace json;
/**
* This function implement a two dimentional map reduce where
* the first level is a distributed storage_proxy class and the
* second level is the stats per scheduling group class.
* @param d - a reference to the storage_proxy distributed class.
* @param mapper - the internal mapper that is used to map the internal
* stat class into a value of type `V`.
* @param reducer - the reducer that is used in both outer and inner
* aggregations.
* @param initial_value - the initial value to use for both aggregations
* @return A future that resolves to the result of the aggregation.
*/
template<typename V, typename Reducer, typename InnerMapper>
future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
InnerMapper mapper, Reducer reducer, V initial_value) {
return d.map_reduce0( [mapper, reducer, initial_value] (const service::storage_proxy& sp) {
return map_reduce_scheduling_group_specific<service::storage_proxy_stats::stats>(
mapper, reducer, initial_value, sp.get_stats_key());
}, initial_value, reducer);
static future<utils::rate_moving_average> sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return d.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average(),
std::plus<utils::rate_moving_average>());
}
/**
* This function implement a two dimentional map reduce where
* the first level is a distributed storage_proxy class and the
* second level is the stats per scheduling group class.
* @param d - a reference to the storage_proxy distributed class.
* @param f - a field pointer which is the implicit internal reducer.
* @param reducer - the reducer that is used in both outer and inner
* aggregations.
* @param initial_value - the initial value to use for both aggregations* @return
* @return A future that resolves to the result of the aggregation.
*/
template<typename V, typename Reducer, typename F>
future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
V F::*f, Reducer reducer, V initial_value) {
return two_dimensional_map_reduce(d, [f] (F& stats) {
return stats.*f;
}, reducer, initial_value);
}
/**
* A partial Specialization of sum_stats for the storage proxy
* case where the get stats function doesn't return a
* stats object with fields but a per scheduling group
* stats object, the name was also changed since functions
* partial specialization is not supported in C++.
*
*/
template<typename V, typename F>
future<json::json_return_type> sum_stats_storage_proxy(distributed<proxy>& d, V F::*f) {
return two_dimensional_map_reduce(d, [f] (F& stats) { return stats.*f; }, std::plus<V>(), V(0)).then([] (V val) {
return make_ready_future<json::json_return_type>(val);
});
}
static future<utils::rate_moving_average> sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).rate();
}, std::plus<utils::rate_moving_average>(), utils::rate_moving_average());
}
static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
httpd::utils_json::rate_moving_average m;
m = val;
@@ -110,89 +51,29 @@ httpd::utils_json::rate_moving_average_and_histogram get_empty_moving_average()
return timer_to_json(utils::rate_moving_average_and_histogram());
}
static future<json::json_return_type> sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
static future<json::json_return_type> sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
return make_ready_future<json::json_return_type>(val.count);
});
}
utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val) {
utils_json::estimated_histogram res;
for (size_t i = 0; i < val.size(); i++) {
res.buckets.push(val.get(i));
res.bucket_offsets.push(val.get_bucket_lower_limit(i));
}
return res;
}
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::time_estimated_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, f, utils::time_estimated_histogram_merge,
utils::time_estimated_histogram()).then([](const utils::time_estimated_histogram& val) {
return make_ready_future<json::json_return_type>(time_to_json_histogram(val));
});
}
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::estimated_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, f, utils::estimated_histogram_merge,
utils::estimated_histogram()).then([](const utils::estimated_histogram& val) {
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::estimated_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return p.get_stats().*f;}, utils::estimated_histogram(),
utils::estimated_histogram_merge).then([](const utils::estimated_histogram& val) {
utils_json::estimated_histogram res;
res = val;
return make_ready_future<json::json_return_type>(res);
});
}
static future<json::json_return_type> total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).hist.mean * (stats.*f).hist.count;
}, std::plus<double>(), 0.0).then([](double val) {
static future<json::json_return_type> total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).hist.mean * (p.get_stats().*f).hist.count;}, 0.0,
std::plus<double>()).then([](double val) {
int64_t res = val;
return make_ready_future<json::json_return_type>(res);
});
}
/**
* A partial Specialization of sum_histogram_stats
* for the storage proxy case where the get stats
* function doesn't return a stats object with
* fields but a per scheduling group stats object,
* the name was also changed since function partial
* specialization is not supported in C++.
*/
template<typename F>
future<json::json_return_type>
sum_histogram_stats_storage_proxy(distributed<proxy>& d,
utils::timed_rate_moving_average_and_histogram F::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).hist;
}, std::plus<utils::ihistogram>(), utils::ihistogram()).
then([](const utils::ihistogram& val) {
return make_ready_future<json::json_return_type>(to_json(val));
});
}
/**
* A partial Specialization of sum_timer_stats for the
* storage proxy case where the get stats function
* doesn't return a stats object with fields but a
* per scheduling group stats object, the name
* was also changed since partial function specialization
* is not supported in C++.
*/
template<typename F>
future<json::json_return_type>
sum_timer_stats_storage_proxy(distributed<proxy>& d,
utils::timed_rate_moving_average_and_histogram F::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).rate();
}, std::plus<utils::rate_moving_average_and_histogram>(),
utils::rate_moving_average_and_histogram()).then([](const utils::rate_moving_average_and_histogram& val) {
return make_ready_future<json::json_return_type>(timer_to_json(val));
});
}
void set_storage_proxy(http_context& ctx, routes& r) {
sp::get_total_hints.set(r, [](std::unique_ptr<request> req) {
//TBD
@@ -201,39 +82,29 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_hinted_handoff_enabled.set(r, [&ctx](std::unique_ptr<request> req) {
const auto& filter = service::get_storage_proxy().local().get_hints_host_filter();
return make_ready_future<json::json_return_type>(!filter.is_disabled_for_all());
auto enabled = ctx.db.local().get_config().hinted_handoff_enabled();
return make_ready_future<json::json_return_type>(enabled);
});
sp::set_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto enable = req->get_query_param("enable");
auto filter = (enable == "true" || enable == "1")
? db::hints::host_filter(db::hints::host_filter::enabled_for_all_tag {})
: db::hints::host_filter(db::hints::host_filter::disabled_for_all_tag {});
return service::get_storage_proxy().invoke_on_all([filter = std::move(filter)] (service::storage_proxy& sp) {
return sp.change_hints_host_filter(filter);
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
return make_ready_future<json::json_return_type>(json_void());
});
sp::get_hinted_handoff_enabled_by_dc.set(r, [](std::unique_ptr<request> req) {
std::vector<sstring> res;
const auto& filter = service::get_storage_proxy().local().get_hints_host_filter();
const auto& dcs = filter.get_dcs();
res.reserve(res.size());
std::copy(dcs.begin(), dcs.end(), std::back_inserter(res));
//TBD
unimplemented();
std::vector<sp::mapper_list> res;
return make_ready_future<json::json_return_type>(res);
});
sp::set_hinted_handoff_enabled_by_dc_list.set(r, [](std::unique_ptr<request> req) {
auto dcs = req->get_query_param("dcs");
auto filter = db::hints::host_filter::parse_from_dc_list(std::move(dcs));
return service::get_storage_proxy().invoke_on_all([filter = std::move(filter)] (service::storage_proxy& sp) {
return sp.change_hints_host_filter(filter);
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
//TBD
unimplemented();
auto enable = req->get_query_param("dcs");
return make_ready_future<json::json_return_type>(json_void());
});
sp::get_max_hint_window.set(r, [](std::unique_ptr<request> req) {
@@ -352,15 +223,15 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_read_repair_attempted.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_attempts);
return sum_stats(ctx.sp, &proxy::stats::read_repair_attempts);
});
sp::get_read_repair_repaired_blocking.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_blocking);
return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_blocking);
});
sp::get_read_repair_repaired_background.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_background);
});
sp::get_schema_versions.set(r, [](std::unique_ptr<request> req) {
@@ -404,10 +275,6 @@ void set_storage_proxy(http_context& ctx, routes& r) {
return sum_stats(ctx.sp, &proxy::stats::cas_write_condition_not_met);
});
sp::get_cas_write_metrics_failed_read_round_optimization.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_failed_read_round_optimization);
});
sp::get_cas_read_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_read_unfinished_commit);
});
@@ -417,71 +284,71 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_read_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_read_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_range_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_histogram_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
return sum_histogram_stats(ctx.sp, &proxy::stats::write);
});
sp::get_read_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
return sum_histogram_stats(ctx.sp, &proxy::stats::read);
});
sp::get_range_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_timer_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
return sum_timer_stats(ctx.sp, &proxy::stats::write);
});
sp::get_cas_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::cas_write);
@@ -500,30 +367,30 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
return sum_timer_stats(ctx.sp, &proxy::stats::read);
});
sp::get_read_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_read);
return sum_estimated_histogram(ctx, &proxy::stats::estimated_read);
});
sp::get_read_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::read);
return total_latency(ctx, &proxy::stats::read);
});
sp::get_write_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_write);
return sum_estimated_histogram(ctx, &proxy::stats::estimated_write);
});
sp::get_write_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::write);
return total_latency(ctx, &proxy::stats::write);
});
sp::get_range_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_timer_stats(ctx.sp, &proxy::stats::range);
});
sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::range);
return total_latency(ctx, &proxy::stats::range);
});
}

View File

@@ -22,7 +22,6 @@
#include "storage_service.hh"
#include "api/api-doc/storage_service.json.hh"
#include "db/config.hh"
#include "db/schema_tables.hh"
#include <optional>
#include <time.h>
#include <boost/range/adaptor/map.hpp>
@@ -42,17 +41,11 @@
#include "sstables/sstables.hh"
#include "database.hh"
#include "db/extensions.hh"
#include "db/snapshot-ctl.hh"
#include "transport/controller.hh"
#include "thrift/controller.hh"
#include "locator/token_metadata.hh"
sstables::sstable::version_types get_highest_supported_format();
namespace api {
const locator::token_metadata& http_context::get_token_metadata() {
return *shared_token_metadata.local().get();
}
namespace ss = httpd::storage_service_json;
using namespace json;
@@ -81,195 +74,35 @@ static ss::token_range token_range_endpoints_to_json(const dht::token_range_endp
return r;
}
using ks_cf_func = std::function<future<json::json_return_type>(http_context&, std::unique_ptr<request>, sstring, std::vector<sstring>)>;
static auto wrap_ks_cf(http_context &ctx, ks_cf_func f) {
return [&ctx, f = std::move(f)](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
if (column_families.empty()) {
column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return f(ctx, std::move(req), std::move(keyspace), std::move(column_families));
};
}
future<json::json_return_type> set_tables_autocompaction(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
if (tables.empty()) {
tables = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return service::get_local_storage_service().set_tables_autocompaction(keyspace, tables, enabled).then([]{
return make_ready_future<json::json_return_type>(json_void());
});
}
void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl) {
ss::start_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.start_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::stop_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.stop_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_native_transport_running.set(r, [&ctl] (std::unique_ptr<request> req) {
return ctl.is_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
}
void unset_transport_controller(http_context& ctx, routes& r) {
ss::start_native_transport.unset(r);
ss::stop_native_transport.unset(r);
ss::is_native_transport_running.unset(r);
}
void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl) {
ss::stop_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.stop_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::start_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.start_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_rpc_server_running.set(r, [&ctl] (std::unique_ptr<request> req) {
return ctl.is_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
}
void unset_rpc_controller(http_context& ctx, routes& r) {
ss::stop_rpc_server.unset(r);
ss::start_rpc_server.unset(r);
ss::is_rpc_server_running.unset(r);
}
void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms) {
ss::repair_async.set(r, [&ctx, &ms](std::unique_ptr<request> req) {
static std::vector<sstring> options = {"primaryRange", "parallelism", "incremental",
"jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "trace",
"startToken", "endToken" };
std::unordered_map<sstring, sstring> options_map;
for (auto o : options) {
auto s = req->get_query_param(o);
if (s != "") {
options_map[o] = s;
}
}
// The repair process is asynchronous: repair_start only starts it and
// returns immediately, not waiting for the repair to finish. The user
// then has other mechanisms to track the ongoing repair's progress,
// or stop it.
return repair_start(ctx.db, ms, validate_keyspace(ctx, req->param),
options_map).then([] (int i) {
return make_ready_future<json::json_return_type>(i);
});
});
ss::get_active_repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
return get_active_repairs(ctx.db).then([] (std::vector<int> res){
return make_ready_future<json::json_return_type>(res);
});
});
ss::repair_async_status.set(r, [&ctx](std::unique_ptr<request> req) {
return repair_get_status(ctx.db, boost::lexical_cast<int>( req->get_query_param("id")))
.then_wrapped([] (future<repair_status>&& fut) {
ss::ns_repair_async_status::return_type_wrapper res;
try {
res = fut.get0();
} catch(std::runtime_error& e) {
throw httpd::bad_param_exception(e.what());
}
return make_ready_future<json::json_return_type>(json::json_return_type(res));
});
});
ss::repair_await_completion.set(r, [&ctx](std::unique_ptr<request> req) {
int id;
using clock = std::chrono::steady_clock;
clock::time_point expire;
try {
id = boost::lexical_cast<int>(req->get_query_param("id"));
// If timeout is not provided, it means no timeout.
sstring s = req->get_query_param("timeout");
int64_t timeout = s.empty() ? int64_t(-1) : boost::lexical_cast<int64_t>(s);
if (timeout < 0 && timeout != -1) {
return make_exception_future<json::json_return_type>(
httpd::bad_param_exception("timeout can only be -1 (means no timeout) or non negative integer"));
}
if (timeout < 0) {
expire = clock::time_point::max();
} else {
expire = clock::now() + std::chrono::seconds(timeout);
}
} catch (std::exception& e) {
return make_exception_future<json::json_return_type>(httpd::bad_param_exception(e.what()));
}
return repair_await_completion(ctx.db, id, expire)
.then_wrapped([] (future<repair_status>&& fut) {
ss::ns_repair_async_status::return_type_wrapper res;
try {
res = fut.get0();
} catch (std::exception& e) {
return make_exception_future<json::json_return_type>(httpd::server_error_exception(e.what()));
}
return make_ready_future<json::json_return_type>(json::json_return_type(res));
});
});
ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
}
void unset_repair(http_context& ctx, routes& r) {
ss::repair_async.unset(r);
ss::get_active_repair_async.unset(r);
ss::repair_async_status.unset(r);
ss::repair_await_completion.unset(r);
ss::force_terminate_all_repair_sessions.unset(r);
ss::force_terminate_all_repair_sessions_new.unset(r);
}
void set_storage_service(http_context& ctx, routes& r) {
using ks_cf_func = std::function<future<json::json_return_type>(std::unique_ptr<request>, sstring, std::vector<sstring>)>;
auto wrap_ks_cf = [&ctx](ks_cf_func f) {
return [&ctx, f = std::move(f)](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
if (column_families.empty()) {
column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return f(std::move(req), std::move(keyspace), std::move(column_families));
};
};
ss::local_hostid.set(r, [](std::unique_ptr<request> req) {
return db::system_keyspace::get_local_host_id().then([](const utils::UUID& id) {
return make_ready_future<json::json_return_type>(id.to_sstring());
});
});
ss::get_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.get_token_metadata().sorted_tokens(), [](const dht::token& i) {
ss::get_tokens.set(r, [] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_metadata().sorted_tokens(), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
});
ss::get_node_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
ss::get_node_tokens.set(r, [] (std::unique_ptr<request> req) {
gms::inet_address addr(req->param["endpoint"]);
return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.get_token_metadata().get_tokens(addr), [](const dht::token& i) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_metadata().get_tokens(addr), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
});
@@ -287,8 +120,8 @@ void set_storage_service(http_context& ctx, routes& r) {
}));
});
ss::get_leaving_nodes.set(r, [&ctx](const_req req) {
return container_to_vec(ctx.get_token_metadata().get_leaving_endpoints());
ss::get_leaving_nodes.set(r, [](const_req req) {
return container_to_vec(service::get_local_storage_service().get_token_metadata().get_leaving_endpoints());
});
ss::get_moving_nodes.set(r, [](const_req req) {
@@ -296,8 +129,8 @@ void set_storage_service(http_context& ctx, routes& r) {
return container_to_vec(addr);
});
ss::get_joining_nodes.set(r, [&ctx](const_req req) {
auto points = ctx.get_token_metadata().get_bootstrap_tokens();
ss::get_joining_nodes.set(r, [](const_req req) {
auto points = service::get_local_storage_service().get_token_metadata().get_bootstrap_tokens();
std::unordered_set<sstring> addr;
for (auto i: points) {
addr.insert(boost::lexical_cast<std::string>(i.second));
@@ -325,26 +158,11 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::get_range_to_endpoint_map.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
std::vector<ss::maplist_mapper> res;
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_range_to_address_map(keyspace),
[](const std::pair<dht::token_range, std::vector<gms::inet_address>>& entry){
ss::maplist_mapper m;
if (entry.first.start()) {
m.key.push(entry.first.start().value().value().to_sstring());
} else {
m.key.push("");
}
if (entry.first.end()) {
m.key.push(entry.first.end().value().value().to_sstring());
} else {
m.key.push("");
}
for (const gms::inet_address& address : entry.second) {
m.value.push(address.to_sstring());
}
return m;
}));
return make_ready_future<json::json_return_type>(res);
});
ss::get_pending_range_to_endpoint_map.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -364,9 +182,10 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(keyspace), token_range_endpoints_to_json));
});
ss::get_host_id_map.set(r, [&ctx](const_req req) {
ss::get_host_id_map.set(r, [](const_req req) {
std::vector<ss::mapper> res;
return map_to_key_value(ctx.get_token_metadata().get_endpoint_to_host_id_map_for_reading(), res);
return map_to_key_value(service::get_local_storage_service().
get_token_metadata().get_endpoint_to_host_id_map_for_reading(), res);
});
ss::get_load.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -399,12 +218,67 @@ void set_storage_service(http_context& ctx, routes& r) {
req.get_query_param("key")));
});
ss::cdc_streams_check_and_repair.set(r, [&ctx] (std::unique_ptr<request> req) {
return service::get_local_storage_service().check_and_repair_cdc_streams().then([] {
ss::get_snapshot_details.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().get_snapshot_details().then([] (auto result) {
std::vector<ss::snapshots> res;
for (auto& map: result) {
ss::snapshots all_snapshots;
all_snapshots.key = map.first;
std::vector<ss::snapshot> snapshot;
for (auto& cf: map.second) {
ss::snapshot s;
s.ks = cf.ks;
s.cf = cf.cf;
s.live = cf.live;
s.total = cf.total;
snapshot.push_back(std::move(s));
}
all_snapshots.value = std::move(snapshot);
res.push_back(std::move(all_snapshots));
}
return make_ready_future<json::json_return_type>(std::move(res));
});
});
ss::take_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_family = req->get_query_param("cf");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
auto resp = make_ready_future<>();
if (column_family.empty()) {
resp = service::get_local_storage_service().take_snapshot(tag, keynames);
} else {
if (keynames.empty()) {
throw httpd::bad_param_exception("The keyspace of column families must be specified");
}
if (keynames.size() > 1) {
throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
}
resp = service::get_local_storage_service().take_column_family_snapshot(keynames[0], column_family, tag);
}
return resp.then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::del_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
return service::get_local_storage_service().clear_snapshot(tag, keynames).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::true_snapshots_size.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().true_snapshots_size().then([] (int64_t size) {
return make_ready_future<json::json_return_type>(size);
});
});
ss::force_keyspace_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
@@ -442,8 +316,8 @@ void set_storage_service(http_context& ctx, routes& r) {
for (auto cf : column_families) {
column_families_vec.push_back(&db.find_column_family(keyspace, cf));
}
return parallel_for_each(column_families_vec, [&cm, &db] (column_family* cf) {
return cm.perform_cleanup(db, cf);
return parallel_for_each(column_families_vec, [&cm] (column_family* cf) {
return cm.perform_cleanup(cf);
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
@@ -451,14 +325,39 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::upgrade_sstables.set(r, wrap_ks_cf(ctx, [] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
ss::scrub.set(r, wrap_ks_cf([&ctx](std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
// TODO: respect this
auto skip_corrupted = req->get_query_param("skip_corrupted");
auto f = make_ready_future<>();
if (!req_param<bool>(*req, "disable_snapshot", false)) {
auto tag = format("pre-scrub-{:d}", db_clock::now().time_since_epoch().count());
f = parallel_for_each(column_families, [keyspace, tag](sstring cf) {
return service::get_local_storage_service().take_column_family_snapshot(keyspace, cf, tag);
});
}
return f.then([&ctx, keyspace, column_families] {
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_scrub(&cf);
});
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
ss::upgrade_sstables.set(r, wrap_ks_cf([&ctx](std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
bool exclude_current_version = req_param<bool>(*req, "exclude_current_version", false);
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_upgrade(db, &cf, exclude_current_version);
return cm.perform_sstable_upgrade(&cf, exclude_current_version);
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
@@ -481,6 +380,59 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
static std::vector<sstring> options = {"primaryRange", "parallelism", "incremental",
"jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "trace",
"startToken", "endToken" };
std::unordered_map<sstring, sstring> options_map;
for (auto o : options) {
auto s = req->get_query_param(o);
if (s != "") {
options_map[o] = s;
}
}
// The repair process is asynchronous: repair_start only starts it and
// returns immediately, not waiting for the repair to finish. The user
// then has other mechanisms to track the ongoing repair's progress,
// or stop it.
return repair_start(ctx.db, validate_keyspace(ctx, req->param),
options_map).then([] (int i) {
return make_ready_future<json::json_return_type>(i);
});
});
ss::get_active_repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
return get_active_repairs(ctx.db).then([] (std::vector<int> res){
return make_ready_future<json::json_return_type>(res);
});
});
ss::repair_async_status.set(r, [&ctx](std::unique_ptr<request> req) {
return repair_get_status(ctx.db, boost::lexical_cast<int>( req->get_query_param("id")))
.then_wrapped([] (future<repair_status>&& fut) {
ss::ns_repair_async_status::return_type_wrapper res;
try {
res = fut.get0();
} catch(std::runtime_error& e) {
throw httpd::bad_param_exception(e.what());
}
return make_ready_future<json::json_return_type>(json::json_return_type(res));
});
});
ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::decommission.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().decommission().then([] {
return make_ready_future<json::json_return_type>(json_void());
@@ -616,6 +568,42 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::stop_rpc_server.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().stop_rpc_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::start_rpc_server.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().start_rpc_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_rpc_server_running.set(r, [] (std::unique_ptr<request> req) {
return service::get_local_storage_service().is_rpc_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
ss::start_native_transport.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().start_native_transport().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::stop_native_transport.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().stop_native_transport().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_native_transport_running.set(r, [] (std::unique_ptr<request> req) {
return service::get_local_storage_service().is_native_transport_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
ss::join_ring.set(r, [](std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(json_void());
});
@@ -738,17 +726,14 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::reset_local_schema.set(r, [](std::unique_ptr<request> req) {
// FIXME: We should truncate schema tables if more than one node in the cluster.
auto& sp = service::get_storage_proxy();
auto& fs = service::get_local_storage_service().features();
return db::schema_tables::recalculate_schema_version(sp, fs).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(json_void());
});
ss::set_trace_probability.set(r, [](std::unique_ptr<request> req) {
auto probability = req->get_query_param("probability");
return futurize_invoke([probability] {
return futurize<json::json_return_type>::apply([probability] {
double real_prob = std::stod(probability.c_str());
return tracing::tracing::tracing_instance().invoke_on_all([real_prob] (auto& local_tracing) {
local_tracing.set_trace_probability(real_prob);
@@ -803,17 +788,19 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto tables = split_cf(req->get_query_param("cf"));
return set_tables_autocompaction(ctx, keyspace, tables, true);
auto column_family = req->get_query_param("cf");
return make_ready_future<json::json_return_type>(json_void());
});
ss::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto tables = split_cf(req->get_query_param("cf"));
return set_tables_autocompaction(ctx, keyspace, tables, false);
auto column_family = req->get_query_param("cf");
return make_ready_future<json::json_return_type>(json_void());
});
ss::deliver_hints.set(r, [](std::unique_ptr<request> req) {
@@ -991,7 +978,7 @@ void set_storage_service(http_context& ctx, routes& r) {
e.value = p.second;
nm.attributes.push(std::move(e));
}
if (!cp->options().contains(compression_parameters::SSTABLE_COMPRESSION)) {
if (!cp->options().count(compression_parameters::SSTABLE_COMPRESSION)) {
ss::mapper e;
e.key = compression_parameters::SSTABLE_COMPRESSION;
e.value = cp->name();
@@ -1049,114 +1036,4 @@ void set_storage_service(http_context& ctx, routes& r) {
}
void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl) {
ss::get_snapshot_details.set(r, [&snap_ctl](std::unique_ptr<request> req) {
return snap_ctl.local().get_snapshot_details().then([] (std::unordered_map<sstring, std::vector<db::snapshot_ctl::snapshot_details>>&& result) {
std::function<future<>(output_stream<char>&&)> f = [result = std::move(result)](output_stream<char>&& s) {
return do_with(output_stream<char>(std::move(s)), true, [&result] (output_stream<char>& s, bool& first){
return s.write("[").then([&s, &first, &result] {
return do_for_each(result, [&s, &first](std::tuple<sstring, std::vector<db::snapshot_ctl::snapshot_details>>&& map){
return do_with(ss::snapshots(), [&s, &first, &map](ss::snapshots& all_snapshots) {
all_snapshots.key = std::get<0>(map);
future<> f = first ? make_ready_future<>() : s.write(", ");
first = false;
std::vector<ss::snapshot> snapshot;
for (auto& cf: std::get<1>(map)) {
ss::snapshot snp;
snp.ks = cf.ks;
snp.cf = cf.cf;
snp.live = cf.live;
snp.total = cf.total;
snapshot.push_back(std::move(snp));
}
all_snapshots.value = std::move(snapshot);
return f.then([&s, &all_snapshots] {
return all_snapshots.write(s);
});
});
});
}).then([&s] {
return s.write("]").then([&s] {
return s.close();
});
});
});
};
return make_ready_future<json::json_return_type>(std::move(f));
});
});
ss::take_snapshot.set(r, [&snap_ctl](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_families = split(req->get_query_param("cf"), ",");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
auto resp = make_ready_future<>();
if (column_families.empty()) {
resp = snap_ctl.local().take_snapshot(tag, keynames);
} else {
if (keynames.empty()) {
throw httpd::bad_param_exception("The keyspace of column families must be specified");
}
if (keynames.size() > 1) {
throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
}
resp = snap_ctl.local().take_column_family_snapshot(keynames[0], column_families, tag);
}
return resp.then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::del_snapshot.set(r, [&snap_ctl](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_family = req->get_query_param("cf");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
return snap_ctl.local().clear_snapshot(tag, keynames, column_family).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::true_snapshots_size.set(r, [&snap_ctl](std::unique_ptr<request> req) {
return snap_ctl.local().true_snapshots_size().then([] (int64_t size) {
return make_ready_future<json::json_return_type>(size);
});
});
ss::scrub.set(r, wrap_ks_cf(ctx, [&snap_ctl] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
const auto skip_corrupted = req_param<bool>(*req, "skip_corrupted", false);
auto f = make_ready_future<>();
if (!req_param<bool>(*req, "disable_snapshot", false)) {
auto tag = format("pre-scrub-{:d}", db_clock::now().time_since_epoch().count());
f = parallel_for_each(column_families, [&snap_ctl, keyspace, tag](sstring cf) {
return snap_ctl.local().take_column_family_snapshot(keyspace, cf, tag);
});
}
return f.then([&ctx, keyspace, column_families, skip_corrupted] {
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_scrub(&cf, skip_corrupted);
});
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
}
void unset_snapshot(http_context& ctx, routes& r) {
ss::get_snapshot_details.unset(r);
ss::take_snapshot.unset(r);
ss::del_snapshot.unset(r);
ss::true_snapshots_size.unset(r);
ss::scrub.unset(r);
}
}

View File

@@ -21,24 +21,10 @@
#pragma once
#include <seastar/core/sharded.hh>
#include "api.hh"
namespace cql_transport { class controller; }
class thrift_controller;
namespace db { class snapshot_ctl; }
namespace netw { class messaging_service; }
namespace api {
void set_storage_service(http_context& ctx, routes& r);
void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
void unset_repair(http_context& ctx, routes& r);
void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl);
void unset_transport_controller(http_context& ctx, routes& r);
void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl);
void unset_rpc_controller(http_context& ctx, routes& r);
void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl);
void unset_snapshot(http_context& ctx, routes& r);
}

View File

@@ -22,7 +22,6 @@
#include "api/api-doc/system.json.hh"
#include "api/api.hh"
#include <seastar/core/reactor.hh>
#include <seastar/http/exception.hh>
#include "log.hh"

View File

@@ -208,7 +208,7 @@ size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t)
external_value_size = cell_view.value_size();
}
// Add overhead of chunk headers. The last one is a special case.
external_value_size += (external_value_size - 1) / data::cell::effective_external_chunk_length * data::cell::external_chunk_overhead;
external_value_size += (external_value_size - 1) / data::cell::maximum_external_chunk_length * data::cell::external_chunk_overhead;
external_value_size += data::cell::external_last_chunk_overhead;
}
return data::cell::structure::serialized_object_size(_data.get(), ctx)

View File

@@ -29,6 +29,7 @@
#include <seastar/net//byteorder.hh>
#include <cstdint>
#include <iosfwd>
#include <seastar/util/gcc6-concepts.hh>
#include "data/cell.hh"
#include "data/schema_info.hh"
#include "imr/utils.hh"
@@ -38,7 +39,6 @@
class abstract_type;
class collection_type_impl;
class atomic_cell_or_collection;
using atomic_cell_value_view = data::value_view;
using atomic_cell_value_mutable_view = data::value_mutable_view;

View File

@@ -26,7 +26,10 @@
namespace auth {
constexpr std::string_view allow_all_authenticator_name("org.apache.cassandra.auth.AllowAllAuthenticator");
const sstring& allow_all_authenticator_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthenticator";
return name;
}
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<

View File

@@ -37,7 +37,7 @@ class migration_manager;
namespace auth {
extern const std::string_view allow_all_authenticator_name;
const sstring& allow_all_authenticator_name();
class allow_all_authenticator final : public authenticator {
public:
@@ -52,8 +52,8 @@ public:
return make_ready_future<>();
}
virtual std::string_view qualified_java_name() const override {
return allow_all_authenticator_name;
virtual const sstring& qualified_java_name() const override {
return allow_all_authenticator_name();
}
virtual bool require_authentication() const override {

View File

@@ -26,7 +26,10 @@
namespace auth {
constexpr std::string_view allow_all_authorizer_name("org.apache.cassandra.auth.AllowAllAuthorizer");
const sstring& allow_all_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthorizer";
return name;
}
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<

View File

@@ -34,7 +34,7 @@ class migration_manager;
namespace auth {
extern const std::string_view allow_all_authorizer_name;
const sstring& allow_all_authorizer_name();
class allow_all_authorizer final : public authorizer {
public:
@@ -49,8 +49,8 @@ public:
return make_ready_future<>();
}
virtual std::string_view qualified_java_name() const override {
return allow_all_authorizer_name;
virtual const sstring& qualified_java_name() const override {
return allow_all_authorizer_name();
}
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override {

View File

@@ -96,7 +96,7 @@ public:
///
/// A fully-qualified (class with package) Java-like name for this implementation.
///
virtual std::string_view qualified_java_name() const = 0;
virtual const sstring& qualified_java_name() const = 0;
virtual bool require_authentication() const = 0;

View File

@@ -100,7 +100,7 @@ public:
///
/// A fully-qualified (class with package) Java-like name for this implementation.
///
virtual std::string_view qualified_java_name() const = 0;
virtual const sstring& qualified_java_name() const = 0;
///
/// Query for the permissions granted directly to a role for a particular \ref resource (and not any of its

View File

@@ -34,9 +34,10 @@ namespace auth {
namespace meta {
constexpr std::string_view AUTH_KS("system_auth");
constexpr std::string_view USERS_CF("users");
constexpr std::string_view AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
const sstring DEFAULT_SUPERUSER_NAME("cassandra");
const sstring AUTH_KS("system_auth");
const sstring USERS_CF("users");
const sstring AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
}
@@ -58,22 +59,22 @@ future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_f
}).discard_result();
}
static future<> create_metadata_table_if_missing_impl(
future<> create_metadata_table_if_missing(
std::string_view table_name,
cql3::query_processor& qp,
std::string_view cql,
::service::migration_manager& mm) {
static auto ignore_existing = [] (seastar::noncopyable_function<future<>()> func) {
return futurize_invoke(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
return futurize_apply(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
};
auto& db = qp.db();
auto parsed_statement = cql3::query_processor::parse_statement(cql);
auto& parsed_cf_statement = static_cast<cql3::statements::raw::cf_statement&>(*parsed_statement);
auto parsed_statement = static_pointer_cast<cql3::statements::raw::cf_statement>(
cql3::query_processor::parse_statement(cql));
parsed_cf_statement.prepare_keyspace(meta::AUTH_KS);
parsed_statement->prepare_keyspace(meta::AUTH_KS);
auto statement = static_pointer_cast<cql3::statements::create_table_statement>(
parsed_cf_statement.prepare(db, qp.get_cql_stats())->statement);
parsed_statement->prepare(db, qp.get_cql_stats())->statement);
const auto schema = statement->get_cf_meta_data(qp.db());
const auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
@@ -84,14 +85,7 @@ static future<> create_metadata_table_if_missing_impl(
return ignore_existing([&mm, table = std::move(table)] () {
return mm.announce_new_column_family(table, false);
});
}
future<> create_metadata_table_if_missing(
std::string_view table_name,
cql3::query_processor& qp,
std::string_view cql,
::service::migration_manager& mm) noexcept {
return futurize_invoke(create_metadata_table_if_missing_impl, table_name, qp, cql, mm);
}
future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db, seastar::abort_source& as) {
@@ -108,17 +102,10 @@ future<> wait_for_schema_agreement(::service::migration_manager& mm, const datab
});
}
::service::query_state& internal_distributed_query_state() noexcept {
#ifdef DEBUG
// Give the much slower debug tests more headroom for completing auth queries.
static const auto t = 30s;
#else
const timeout_config& internal_distributed_timeout_config() noexcept {
static const auto t = 5s;
#endif
static const timeout_config tc{t, t, t, t, t, t, t};
static thread_local ::service::client_state cs(::service::client_state::internal_tag{}, tc);
static thread_local ::service::query_state qs(cs, empty_service_permit());
return qs;
return tc;
}
}

View File

@@ -27,15 +27,13 @@
#include <seastar/core/future.hh>
#include <seastar/core/abort_source.hh>
#include <seastar/util/noncopyable_function.hh>
#include <seastar/core/seastar.hh>
#include <seastar/core/reactor.hh>
#include <seastar/core/resource.hh>
#include <seastar/core/sstring.hh>
#include <seastar/core/smp.hh>
#include "log.hh"
#include "seastarx.hh"
#include "utils/exponential_backoff_retry.hh"
#include "service/query_state.hh"
using namespace std::chrono_literals;
@@ -54,16 +52,16 @@ namespace auth {
namespace meta {
constexpr std::string_view DEFAULT_SUPERUSER_NAME("cassandra");
extern const std::string_view AUTH_KS;
extern const std::string_view USERS_CF;
extern const std::string_view AUTH_PACKAGE_NAME;
extern const sstring DEFAULT_SUPERUSER_NAME;
extern const sstring AUTH_KS;
extern const sstring USERS_CF;
extern const sstring AUTH_PACKAGE_NAME;
}
template <class Task>
future<> once_among_shards(Task&& f) {
if (this_shard_id() == 0u) {
if (engine().cpu_id() == 0u) {
return f();
}
@@ -81,13 +79,13 @@ future<> create_metadata_table_if_missing(
std::string_view table_name,
cql3::query_processor&,
std::string_view cql,
::service::migration_manager&) noexcept;
::service::migration_manager&);
future<> wait_for_schema_agreement(::service::migration_manager&, const database&, seastar::abort_source&);
///
/// Time-outs for internal, non-local CQL queries.
///
::service::query_state& internal_distributed_query_state() noexcept;
const timeout_config& internal_distributed_timeout_config() noexcept;
}

View File

@@ -51,7 +51,7 @@ extern "C" {
#include <boost/algorithm/string/join.hpp>
#include <boost/range.hpp>
#include <seastar/core/seastar.hh>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
@@ -65,14 +65,15 @@ extern "C" {
namespace auth {
std::string_view default_authorizer::qualified_java_name() const {
return "org.apache.cassandra.auth.CassandraAuthorizer";
const sstring& default_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "CassandraAuthorizer";
return name;
}
static constexpr std::string_view ROLE_NAME = "role";
static constexpr std::string_view RESOURCE_NAME = "resource";
static constexpr std::string_view PERMISSIONS_NAME = "permissions";
static constexpr std::string_view PERMISSIONS_CF = "role_permissions";
static const sstring ROLE_NAME = "role";
static const sstring RESOURCE_NAME = "resource";
static const sstring PERMISSIONS_NAME = "permissions";
static const sstring PERMISSIONS_CF = "role_permissions";
static logging::logger alogger("default_authorizer");
@@ -100,9 +101,10 @@ bool default_authorizer::legacy_metadata_exists() const {
future<bool> default_authorizer::any_granted() const {
static const sstring query = format("SELECT * FROM {}.{} LIMIT 1", meta::AUTH_KS, PERMISSIONS_CF);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{},
true).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return !results->empty();
@@ -113,9 +115,10 @@ future<> default_authorizer::migrate_legacy_metadata() const {
alogger.info("Starting migration of legacy permissions metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::LOCAL_ONE).then([this](::shared_ptr<cql3::untyped_result_set> results) {
db::consistency_level::LOCAL_ONE,
infinite_timeout_config).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
return do_with(
row.get_as<sstring>("username"),
@@ -192,9 +195,10 @@ default_authorizer::authorize(const role_or_anonymous& maybe_role, const resourc
ROLE_NAME,
RESOURCE_NAME);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{*maybe_role.name, r.name()}).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return permissions::NONE;
@@ -220,10 +224,10 @@ default_authorizer::modify(
ROLE_NAME,
RESOURCE_NAME),
[this, &role_name, set, &resource](const auto& query) {
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{permissions::to_strings(set), sstring(role_name), resource.name()}).discard_result();
});
}
@@ -245,10 +249,10 @@ future<std::vector<permission_details>> default_authorizer::list_all() const {
meta::AUTH_KS,
PERMISSIONS_CF);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
std::vector<permission_details> all_details;
@@ -272,10 +276,10 @@ future<> default_authorizer::revoke_all(std::string_view role_name) const {
PERMISSIONS_CF,
ROLE_NAME);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result().handle_exception([role_name](auto ep) {
try {
std::rethrow_exception(ep);
@@ -292,9 +296,10 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
PERMISSIONS_CF,
RESOURCE_NAME);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{resource.name()}).then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
@@ -308,9 +313,10 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
ROLE_NAME,
RESOURCE_NAME);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{r.get_as<sstring>(ROLE_NAME), resource.name()}).discard_result().handle_exception(
[resource](auto ep) {
try {

View File

@@ -51,6 +51,8 @@
namespace auth {
const sstring& default_authorizer_name();
class default_authorizer : public authorizer {
cql3::query_processor& _qp;
@@ -69,7 +71,9 @@ public:
virtual future<> stop() override;
virtual std::string_view qualified_java_name() const override;
virtual const sstring& qualified_java_name() const override {
return default_authorizer_name();
}
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override;

View File

@@ -48,7 +48,7 @@
#include <optional>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <seastar/core/seastar.hh>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
@@ -62,13 +62,15 @@
namespace auth {
constexpr std::string_view password_authenticator_name("org.apache.cassandra.auth.PasswordAuthenticator");
const sstring& password_authenticator_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "PasswordAuthenticator";
return name;
}
// name of the hash column.
static constexpr std::string_view SALTED_HASH = "salted_hash";
static constexpr std::string_view OPTIONS = "options";
static constexpr std::string_view DEFAULT_USER_NAME = meta::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = sstring(meta::DEFAULT_SUPERUSER_NAME);
static const sstring SALTED_HASH = "salted_hash";
static const sstring DEFAULT_USER_NAME = meta::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = meta::DEFAULT_SUPERUSER_NAME;
static logging::logger plogger("password_authenticator");
@@ -94,13 +96,10 @@ static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
return !row.get_or<sstring>(SALTED_HASH, "").empty();
}
static const sstring& update_row_query() {
static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name,
SALTED_HASH,
meta::roles_table::role_col_name);
return update_row_query;
}
static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
static const sstring legacy_table_name{"credentials"};
@@ -112,18 +111,18 @@ future<> password_authenticator::migrate_legacy_metadata() const {
plogger.info("Starting migration of legacy authentication metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
auto username = row.get_as<sstring>("username");
auto salted_hash = row.get_as<sstring>(SALTED_HASH);
return _qp.execute_internal(
update_row_query(),
return _qp.process(
update_row_query,
consistency_for_user(username),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{std::move(salted_hash), username}).discard_result();
}).finally([results] {});
}).then([] {
@@ -137,10 +136,10 @@ future<> password_authenticator::migrate_legacy_metadata() const {
future<> password_authenticator::create_default_if_missing() const {
return default_role_row_satisfies(_qp, &has_salted_hash).then([this](bool exists) {
if (!exists) {
return _qp.execute_internal(
update_row_query(),
return _qp.process(
update_row_query,
db::consistency_level::QUORUM,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{passwords::hash(DEFAULT_USER_PASSWORD, rng_for_salt), DEFAULT_USER_NAME}).then([](auto&&) {
plogger.info("Created default superuser authentication record.");
});
@@ -195,8 +194,8 @@ db::consistency_level password_authenticator::consistency_for_user(std::string_v
return db::consistency_level::LOCAL_ONE;
}
std::string_view password_authenticator::qualified_java_name() const {
return password_authenticator_name;
const sstring& password_authenticator::qualified_java_name() const {
return password_authenticator_name();
}
bool password_authenticator::require_authentication() const {
@@ -204,19 +203,19 @@ bool password_authenticator::require_authentication() const {
}
authentication_option_set password_authenticator::supported_options() const {
return authentication_option_set{authentication_option::password, authentication_option::options};
return authentication_option_set{authentication_option::password};
}
authentication_option_set password_authenticator::alterable_options() const {
return authentication_option_set{authentication_option::password, authentication_option::options};
return authentication_option_set{authentication_option::password};
}
future<authenticated_user> password_authenticator::authenticate(
const credentials_map& credentials) const {
if (!credentials.contains(USERNAME_KEY)) {
if (!credentials.count(USERNAME_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", USERNAME_KEY));
}
if (!credentials.contains(PASSWORD_KEY)) {
if (!credentials.count(PASSWORD_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", PASSWORD_KEY));
}
@@ -228,16 +227,16 @@ future<authenticated_user> password_authenticator::authenticate(
// obsolete prepared statements pretty quickly.
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return futurize_invoke([this, username, password] {
return futurize_apply([this, username, password] {
static const sstring query = format("SELECT {} FROM {} WHERE {} = ?",
SALTED_HASH,
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_user(username),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{username},
true);
}).then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
@@ -263,91 +262,49 @@ future<authenticated_user> password_authenticator::authenticate(
});
}
future<> password_authenticator::maybe_update_custom_options(std::string_view role_name, const authentication_options& options) const {
static const sstring query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name,
OPTIONS,
meta::roles_table::role_col_name);
if (!options.options) {
future<> password_authenticator::create(std::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return make_ready_future<>();
}
std::vector<std::pair<data_value, data_value>> entries;
for (const auto& entry : *options.options) {
entries.push_back({data_value(entry.first), data_value(entry.second)});
}
auto map_value = make_map_value(map_type_impl::get_instance(utf8_type, utf8_type, false), entries);
return _qp.execute_internal(
query,
return _qp.process(
update_row_query,
consistency_for_user(role_name),
internal_distributed_query_state(),
{std::move(map_value), sstring(role_name)}).discard_result();
}
future<> password_authenticator::create(std::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return maybe_update_custom_options(role_name, options);
}
return _qp.execute_internal(
update_row_query(),
consistency_for_user(role_name),
internal_distributed_query_state(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result().then([this, role_name, &options] {
return maybe_update_custom_options(role_name, options);
});
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
}
future<> password_authenticator::alter(std::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return maybe_update_custom_options(role_name, options);
return make_ready_future<>();
}
static const sstring query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_user(role_name),
internal_distributed_query_state(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result().then([this, role_name, &options] {
return maybe_update_custom_options(role_name, options);
}).discard_result();
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
}
future<> password_authenticator::drop(std::string_view name) const {
static const sstring query = format("DELETE {} FROM {} WHERE {} = ?",
SALTED_HASH,
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query, consistency_for_user(name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(name)}).discard_result();
}
future<custom_options> password_authenticator::query_custom_options(std::string_view role_name) const {
static const sstring query = format("SELECT {} FROM {} WHERE {} = ?",
OPTIONS,
meta::roles_table::qualified_name,
meta::roles_table::role_col_name);
return _qp.execute_internal(
query, consistency_for_user(role_name),
internal_distributed_query_state(),
{sstring(role_name)}).then([](::shared_ptr<cql3::untyped_result_set> rs) {
custom_options opts;
const auto& row = rs->one();
if (row.has(OPTIONS)) {
row.get_map_data<sstring, sstring>(OPTIONS, std::inserter(opts, opts.end()), utf8_type, utf8_type);
}
return opts;
});
return make_ready_future<custom_options>();
}
const resource_set& password_authenticator::protected_resources() const {

View File

@@ -52,7 +52,7 @@ class migration_manager;
namespace auth {
extern const std::string_view password_authenticator_name;
const sstring& password_authenticator_name();
class password_authenticator : public authenticator {
cql3::query_processor& _qp;
@@ -71,7 +71,7 @@ public:
virtual future<> stop() override;
virtual std::string_view qualified_java_name() const override;
virtual const sstring& qualified_java_name() const override;
virtual bool require_authentication() const override;
@@ -94,8 +94,6 @@ public:
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
private:
future<> maybe_update_custom_options(std::string_view role_name, const authentication_options& options) const;
bool legacy_metadata_exists() const;
future<> migrate_legacy_metadata() const;

View File

@@ -43,16 +43,18 @@ std::string_view creation_query() {
" can_login boolean,"
" is_superuser boolean,"
" member_of set<text>,"
" salted_hash text,"
" options frozen<map<text, text>>,"
" salted_hash text"
")",
qualified_name,
qualified_name(),
role_col_name);
return instance;
}
constexpr std::string_view qualified_name("system_auth.roles");
std::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
}
@@ -62,20 +64,21 @@ future<bool> default_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = format("SELECT * FROM {} WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return do_with(std::move(p), [&qp](const auto& p) {
return qp.execute_internal(
return qp.process(
query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&qp, &p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return qp.execute_internal(
return qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
@@ -94,13 +97,13 @@ future<bool> default_role_row_satisfies(
future<bool> any_nondefault_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = format("SELECT * FROM {}", meta::roles_table::qualified_name);
static const sstring query = format("SELECT * FROM {}", meta::roles_table::qualified_name());
return do_with(std::move(p), [&qp](const auto& p) {
return qp.execute_internal(
return qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state()).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
internal_distributed_timeout_config()).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return false;
}

View File

@@ -43,7 +43,7 @@ std::string_view creation_query();
constexpr std::string_view name{"roles", 5};
extern const std::string_view qualified_name;
std::string_view qualified_name() noexcept;
constexpr std::string_view role_col_name{"role", 4};

View File

@@ -31,7 +31,9 @@
#include "auth/allow_all_authenticator.hh"
#include "auth/allow_all_authorizer.hh"
#include "auth/common.hh"
#include "auth/password_authenticator.hh"
#include "auth/role_or_anonymous.hh"
#include "auth/standard_role_manager.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "db/consistency_level_type.hh"
@@ -123,7 +125,18 @@ service::service(
, _authorizer(std::move(z))
, _authenticator(std::move(a))
, _role_manager(std::move(r))
, _migration_listener(std::make_unique<auth_migration_listener>(*_authorizer)) {}
, _migration_listener(std::make_unique<auth_migration_listener>(*_authorizer)) {
// The password authenticator requires that the `standard_role_manager` is running so that the roles metadata table
// it manages is created and updated. This cross-module dependency is rather gross, but we have to maintain it for
// the sake of compatibility with Apache Cassandra and its choice of auth. schema.
if ((_authenticator->qualified_java_name() == password_authenticator_name())
&& (_role_manager->qualified_java_name() != standard_role_manager_name())) {
throw incompatible_module_combination(
format("The {} authenticator must be loaded alongside the {} role-manager.",
password_authenticator_name(),
standard_role_manager_name()));
}
}
service::service(
permissions_cache_config c,
@@ -165,7 +178,7 @@ future<> service::start(::service::migration_manager& mm) {
return create_keyspace_if_missing(mm);
}).then([this] {
return _role_manager->start().then([this] {
return when_all_succeed(_authorizer->start(), _authenticator->start()).discard_result();
return when_all_succeed(_authorizer->start(), _authenticator->start());
});
}).then([this] {
_permissions_cache = std::make_unique<permissions_cache>(_permissions_cache_config, *this, log);
@@ -181,12 +194,9 @@ future<> service::stop() {
// Only one of the shards has the listener registered, but let's try to
// unregister on each one just to make sure.
return _mnotifier.unregister_listener(_migration_listener.get()).then([this] {
if (_permissions_cache) {
return _permissions_cache->stop();
}
return make_ready_future<>();
return _permissions_cache->stop();
}).then([this] {
return when_all_succeed(_role_manager->stop(), _authorizer->stop(), _authenticator->stop()).discard_result();
return when_all_succeed(_role_manager->stop(), _authorizer->stop(), _authenticator->stop());
});
}
@@ -207,27 +217,30 @@ future<bool> service::has_existing_legacy_users() const {
// This logic is borrowed directly from Apache Cassandra. By first checking for the presence of the default user, we
// can potentially avoid doing a range query with a high consistency level.
return _qp.execute_internal(
return _qp.process(
default_user_query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
return make_ready_future<bool>(true);
}
return _qp.execute_internal(
return _qp.process(
default_user_query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
return make_ready_future<bool>(true);
}
return _qp.execute_internal(
return _qp.process(
all_users_query,
db::consistency_level::QUORUM).then([](auto results) {
db::consistency_level::QUORUM,
infinite_timeout_config).then([](auto results) {
return make_ready_future<bool>(!results->empty());
});
});
@@ -360,28 +373,25 @@ future<permission_set> get_permissions(const service& ser, const authenticated_u
}
bool is_enforcing(const service& ser) {
const bool enforcing_authorizer = ser.underlying_authorizer().qualified_java_name() != allow_all_authorizer_name;
const bool enforcing_authorizer = ser.underlying_authorizer().qualified_java_name() != allow_all_authorizer_name();
const bool enforcing_authenticator = ser.underlying_authenticator().qualified_java_name()
!= allow_all_authenticator_name;
!= allow_all_authenticator_name();
return enforcing_authorizer || enforcing_authenticator;
}
bool is_protected(const service& ser, command_desc cmd) noexcept {
if (cmd.type_ == command_desc::type::ALTER_WITH_OPTS) {
return false; // Table attributes are OK to modify; see #7057.
}
return ser.underlying_role_manager().protected_resources().contains(cmd.resource)
|| ser.underlying_authenticator().protected_resources().contains(cmd.resource)
|| ser.underlying_authorizer().protected_resources().contains(cmd.resource);
bool is_protected(const service& ser, const resource& r) noexcept {
return ser.underlying_role_manager().protected_resources().count(r)
|| ser.underlying_authenticator().protected_resources().count(r)
|| ser.underlying_authorizer().protected_resources().count(r);
}
static void validate_authentication_options_are_supported(
const authentication_options& options,
const authentication_option_set& supported) {
const auto check = [&supported](authentication_option k) {
if (!supported.contains(k)) {
if (supported.count(k) == 0) {
throw unsupported_authentication_option(k);
}
};
@@ -406,7 +416,7 @@ future<> create_role(
return make_ready_future<>();
}
return futurize_invoke(
return futurize_apply(
&validate_authentication_options_are_supported,
options,
ser.underlying_authenticator().supported_options()).then([&ser, name, &options] {
@@ -430,7 +440,7 @@ future<> alter_role(
return make_ready_future<>();
}
return futurize_invoke(
return futurize_apply(
&validate_authentication_options_are_supported,
options,
ser.underlying_authenticator().supported_options()).then([&ser, name, &options] {
@@ -445,9 +455,7 @@ future<> drop_role(const service& ser, std::string_view name) {
return when_all_succeed(
a.revoke_all(name),
a.revoke_all(r))
.discard_result()
.handle_exception_type([](const unsupported_authorization_operation&) {
a.revoke_all(r)).handle_exception_type([](const unsupported_authorization_operation&) {
// Nothing.
});
}).then([&ser, name] {
@@ -460,8 +468,8 @@ future<> drop_role(const service& ser, std::string_view name) {
future<bool> has_role(const service& ser, std::string_view grantee, std::string_view name) {
return when_all_succeed(
validate_role_exists(ser, name),
ser.get_roles(grantee)).then_unpack([name](role_set all_roles) {
return make_ready_future<bool>(all_roles.contains(sstring(name)));
ser.get_roles(grantee)).then([name](role_set all_roles) {
return make_ready_future<bool>(all_roles.count(sstring(name)) != 0);
});
}
future<bool> has_role(const service& ser, const authenticated_user& u, std::string_view name) {
@@ -518,9 +526,14 @@ future<std::vector<permission_details>> list_filtered_permissions(
? auth::expand_resource_family(r)
: auth::resource_set{r};
std::erase_if(all_details, [&resources](const permission_details& pd) {
return !resources.contains(pd.resource);
});
all_details.erase(
std::remove_if(
all_details.begin(),
all_details.end(),
[&resources](const permission_details& pd) {
return resources.count(pd.resource) == 0;
}),
all_details.end());
}
std::transform(
@@ -533,9 +546,11 @@ future<std::vector<permission_details>> list_filtered_permissions(
});
// Eliminate rows with an empty permission set.
std::erase_if(all_details, [](const permission_details& pd) {
return pd.permissions.mask() == 0;
});
all_details.erase(
std::remove_if(all_details.begin(), all_details.end(), [](const permission_details& pd) {
return pd.permissions.mask() == 0;
}),
all_details.end());
if (!role_name) {
return make_ready_future<std::vector<permission_details>>(std::move(all_details));
@@ -547,9 +562,14 @@ future<std::vector<permission_details>> list_filtered_permissions(
return do_with(std::move(all_details), [&ser, role_name](auto& all_details) {
return ser.get_roles(*role_name).then([&all_details](role_set all_roles) {
std::erase_if(all_details, [&all_roles](const permission_details& pd) {
return !all_roles.contains(pd.role_name);
});
all_details.erase(
std::remove_if(
all_details.begin(),
all_details.end(),
[&all_roles](const permission_details& pd) {
return all_roles.count(pd.role_name) == 0;
}),
all_details.end());
return make_ready_future<std::vector<permission_details>>(std::move(all_details));
});

View File

@@ -181,21 +181,10 @@ future<permission_set> get_permissions(const service&, const authenticated_user&
///
bool is_enforcing(const service&);
/// A description of a CQL command from which auth::service can tell whether or not this command could endanger
/// internal data on which auth::service depends.
struct command_desc {
auth::permission permission; ///< Nature of the command's alteration.
const ::auth::resource& resource; ///< Resource impacted by this command.
enum class type {
ALTER_WITH_OPTS, ///< Command is ALTER ... WITH ...
OTHER
} type_ = type::OTHER;
};
///
/// Protected resources cannot be modified even if the performer has permissions to do so.
///
bool is_protected(const service&, command_desc) noexcept;
bool is_protected(const service&, const resource&) noexcept;
///
/// Create a role with optional authentication information.

View File

@@ -35,7 +35,6 @@
#include "auth/common.hh"
#include "auth/roles-metadata.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "db/consistency_level_type.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
@@ -49,7 +48,11 @@ namespace meta {
namespace role_members_table {
constexpr std::string_view name{"role_members" , 12};
constexpr std::string_view qualified_name("system_auth.role_members");
static std::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
}
@@ -80,13 +83,13 @@ static db::consistency_level consistency_for_role(std::string_view role_name) no
static future<std::optional<record>> find_record(cql3::query_processor& qp, std::string_view role_name) {
static const sstring query = format("SELECT * FROM {} WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return qp.execute_internal(
return qp.process(
query,
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name)},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
@@ -120,8 +123,13 @@ static bool has_can_login(const cql3::untyped_result_set_row& row) {
return row.has("can_login") && !(boolean_type->deserialize(row.get_blob("can_login")).is_null());
}
std::string_view standard_role_manager_name() noexcept {
static const sstring instance = meta::AUTH_PACKAGE_NAME + "CassandraRoleManager";
return instance;
}
std::string_view standard_role_manager::qualified_java_name() const noexcept {
return "org.apache.cassandra.auth.CassandraRoleManager";
return standard_role_manager_name();
}
const resource_set& standard_role_manager::protected_resources() const {
@@ -139,7 +147,7 @@ future<> standard_role_manager::create_metadata_tables_if_missing() const {
" member text,"
" PRIMARY KEY (role, member)"
")",
meta::role_members_table::qualified_name);
meta::role_members_table::qualified_name());
return when_all_succeed(
@@ -152,20 +160,20 @@ future<> standard_role_manager::create_metadata_tables_if_missing() const {
meta::role_members_table::name,
_qp,
create_role_members_query,
_migration_manager)).discard_result();
_migration_manager));
}
future<> standard_role_manager::create_default_role_if_missing() const {
return default_role_row_satisfies(_qp, &has_can_login).then([this](bool exists) {
if (!exists) {
static const sstring query = format("INSERT INTO {} ({}, is_superuser, can_login) VALUES (?, true, true)",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{meta::DEFAULT_SUPERUSER_NAME}).then([](auto&&) {
log.info("Created default superuser role '{}'.", meta::DEFAULT_SUPERUSER_NAME);
return make_ready_future<>();
@@ -189,10 +197,10 @@ future<> standard_role_manager::migrate_legacy_metadata() const {
log.info("Starting migration of legacy user metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
role_config config;
config.is_superuser = row.get_or<bool>("super", false);
@@ -247,13 +255,13 @@ future<> standard_role_manager::stop() {
future<> standard_role_manager::create_or_replace(std::string_view role_name, const role_config& c) const {
static const sstring query = format("INSERT INTO {} ({}, is_superuser, can_login) VALUES (?, ?, ?)",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name), c.is_superuser, c.can_login},
true).discard_result();
}
@@ -290,13 +298,13 @@ standard_role_manager::alter(std::string_view role_name, const role_config_updat
return make_ready_future<>();
}
return _qp.execute_internal(
return _qp.process(
format("UPDATE {} SET {} WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
build_column_assignments(u),
meta::roles_table::role_col_name),
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result();
});
}
@@ -310,12 +318,12 @@ future<> standard_role_manager::drop(std::string_view role_name) const {
// First, revoke this role from all roles that are members of it.
const auto revoke_from_members = [this, role_name] {
static const sstring query = format("SELECT member FROM {} WHERE role = ?",
meta::role_members_table::qualified_name);
meta::role_members_table::qualified_name());
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name)}).then([this, role_name](::shared_ptr<cql3::untyped_result_set> members) {
return parallel_for_each(
members->begin(),
@@ -348,17 +356,17 @@ future<> standard_role_manager::drop(std::string_view role_name) const {
// Finally, delete the role itself.
auto delete_role = [this, role_name] {
static const sstring query = format("DELETE FROM {} WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result();
};
return when_all_succeed(revoke_from_members(), revoke_members_of()).then_unpack([delete_role = std::move(delete_role)] {
return when_all_succeed(revoke_from_members(), revoke_members_of()).then([delete_role = std::move(delete_role)] {
return delete_role();
});
});
@@ -374,40 +382,40 @@ standard_role_manager::modify_membership(
const auto modify_roles = [this, role_name, grantee_name, ch] {
const auto query = format(
"UPDATE {} SET member_of = member_of {} ? WHERE {} = ?",
meta::roles_table::qualified_name,
meta::roles_table::qualified_name(),
(ch == membership_change::add ? '+' : '-'),
meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
consistency_for_role(grantee_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{role_set{sstring(role_name)}, sstring(grantee_name)}).discard_result();
};
const auto modify_role_members = [this, role_name, grantee_name, ch] {
switch (ch) {
case membership_change::add:
return _qp.execute_internal(
return _qp.process(
format("INSERT INTO {} (role, member) VALUES (?, ?)",
meta::role_members_table::qualified_name),
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name), sstring(grantee_name)}).discard_result();
case membership_change::remove:
return _qp.execute_internal(
return _qp.process(
format("DELETE FROM {} WHERE role = ? AND member = ?",
meta::role_members_table::qualified_name),
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
internal_distributed_query_state(),
internal_distributed_timeout_config(),
{sstring(role_name), sstring(grantee_name)}).discard_result();
}
return make_ready_future<>();
};
return when_all_succeed(modify_roles(), modify_role_members).discard_result();
return when_all_succeed(modify_roles(), modify_role_members());
}
future<>
@@ -416,7 +424,7 @@ standard_role_manager::grant(std::string_view grantee_name, std::string_view rol
return this->query_granted(
grantee_name,
recursive_role_query::yes).then([role_name, grantee_name](role_set roles) {
if (roles.contains(sstring(role_name))) {
if (roles.count(sstring(role_name)) != 0) {
throw role_already_included(grantee_name, role_name);
}
@@ -428,7 +436,7 @@ standard_role_manager::grant(std::string_view grantee_name, std::string_view rol
return this->query_granted(
role_name,
recursive_role_query::yes).then([role_name, grantee_name](role_set roles) {
if (roles.contains(sstring(grantee_name))) {
if (roles.count(sstring(grantee_name)) != 0) {
throw role_already_included(role_name, grantee_name);
}
@@ -436,7 +444,7 @@ standard_role_manager::grant(std::string_view grantee_name, std::string_view rol
});
};
return when_all_succeed(check_redundant(), check_cycle()).then_unpack([this, role_name, grantee_name] {
return when_all_succeed(check_redundant(), check_cycle()).then([this, role_name, grantee_name] {
return this->modify_membership(grantee_name, role_name, membership_change::add);
});
}
@@ -451,7 +459,7 @@ standard_role_manager::revoke(std::string_view revokee_name, std::string_view ro
return this->query_granted(
revokee_name,
recursive_role_query::no).then([revokee_name, role_name](role_set roles) {
if (!roles.contains(sstring(role_name))) {
if (roles.count(sstring(role_name)) == 0) {
throw revoke_ungranted_role(revokee_name, role_name);
}
@@ -495,15 +503,15 @@ future<role_set> standard_role_manager::query_granted(std::string_view grantee_n
future<role_set> standard_role_manager::query_all() const {
static const sstring query = format("SELECT {} FROM {}",
meta::roles_table::role_col_name,
meta::roles_table::qualified_name);
meta::roles_table::qualified_name());
// To avoid many copies of a view.
static const auto role_col_name_string = sstring(meta::roles_table::role_col_name);
return _qp.execute_internal(
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_query_state()).then([](::shared_ptr<cql3::untyped_result_set> results) {
internal_distributed_timeout_config()).then([](::shared_ptr<cql3::untyped_result_set> results) {
role_set roles;
std::transform(

View File

@@ -42,6 +42,8 @@ class migration_manager;
namespace auth {
std::string_view standard_role_manager_name() noexcept;
class standard_role_manager final : public role_manager {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;

View File

@@ -82,7 +82,7 @@ public:
return _authenticator->stop();
}
virtual std::string_view qualified_java_name() const override {
virtual const sstring& qualified_java_name() const override {
return transitional_authenticator_name();
}
@@ -101,7 +101,7 @@ public:
virtual future<authenticated_user> authenticate(const credentials_map& credentials) const override {
auto i = credentials.find(authenticator::USERNAME_KEY);
if ((i == credentials.end() || i->second.empty())
&& (!credentials.contains(PASSWORD_KEY) || credentials.at(PASSWORD_KEY).empty())) {
&& (!credentials.count(PASSWORD_KEY) || credentials.at(PASSWORD_KEY).empty())) {
// return anon user
return make_ready_future<authenticated_user>(anonymous_user());
}
@@ -158,7 +158,7 @@ public:
}
virtual future<authenticated_user> get_authenticated_user() const {
return futurize_invoke([this] {
return futurize_apply([this] {
return _sasl->get_authenticated_user().handle_exception([](auto ep) {
try {
std::rethrow_exception(ep);
@@ -201,7 +201,7 @@ public:
return _authorizer->stop();
}
virtual std::string_view qualified_java_name() const override {
virtual const sstring& qualified_java_name() const override {
return transitional_authorizer_name();
}

Some files were not shown because too many files have changed in this diff Show More